{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/image-classification/papers/43","list_of":"/task/image-classification","task":"Image Classification","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":43,"pages_in_order":105,"rows_per_page":100,"rows":[4201,4300],"of":10488,"counts":{"archive_papers_tagged":10488,"with_a_code_link":4702,"where_syntology_ran_a_sample":1392,"not_listed_spam_title":0,"listed":10488,"listed_where_code_ran":1392,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":1164,"every_run_a_failure_of_syntologys_instrument":228,"listed_with_a_run_with_no_instrument_failure":1164,"listed_every_run_a_failure_of_syntologys_instrument":228,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/image-classification","prev":"/task/image-classification/papers/42","next":"/task/image-classification/papers/44","papers":[{"url":"/paper/outside-the-box-abstraction-based-monitoring","slug":"outside-the-box-abstraction-based-monitoring","title":"Outside the Box: Abstraction-Based Monitoring of Neural Networks","date":"2019-11-20","arxiv_id":"1911.09032","repositories_listed":1,"syntology":null},{"url":"/paper/reliability-does-matter-an-end-to-end-weakly","slug":"reliability-does-matter-an-end-to-end-weakly","title":"Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approach","date":"2019-11-19","arxiv_id":"1911.08039","repositories_listed":1,"syntology":null},{"url":"/paper/rethinking-deep-active-learning-using-1","slug":"rethinking-deep-active-learning-using-1","title":"Rethinking deep active learning: Using unlabeled data at model training","date":"2019-11-19","arxiv_id":"1911.08177","repositories_listed":1,"syntology":{"n":21,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":5,"n_honours":2,"n_violates":0,"n_no_contract":13,"n_pointer_only":3,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/rethinking-deep-active-learning-using-1#ran","syntology_url":"https://syntology.ai/paper/1911.08177","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08177"}},"official":{"repos":["osimeoni/RethinkingDeepActiveLearning"],"state":"official (archive's flag): 16 ran","n_ran":16,"n_constructed":0,"n_ran_no_instrument_failure":15,"n_unverified":5,"ran_from_kinds":["official"]}}},{"url":"/paper/constructing-multiple-tasks-for-augmentation","slug":"constructing-multiple-tasks-for-augmentation","title":"Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features","date":"2019-11-18","arxiv_id":"1911.07518","repositories_listed":1,"syntology":null},{"url":"/paper/learning-permutation-invariant","slug":"learning-permutation-invariant","title":"Learning Permutation Invariant Representations using Memory Networks","date":"2019-11-18","arxiv_id":"1911.07984","repositories_listed":1,"syntology":null},{"url":"/paper/segmentation-guided-attention-network-for","slug":"segmentation-guided-attention-network-for","title":"Crowd Counting via Segmentation Guided Attention Networks and Curriculum Loss","date":"2019-11-18","arxiv_id":"1911.07990","repositories_listed":1,"syntology":null},{"url":"/paper/meta-reinforced-synthetic-data-for-one-shot-1","slug":"meta-reinforced-synthetic-data-for-one-shot-1","title":"Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition","date":"2019-11-17","arxiv_id":"1911.07164","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/meta-reinforced-synthetic-data-for-one-shot-1#ran","syntology_url":"https://syntology.ai/paper/1911.07164","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.07164"}},"official":{"repos":["apple2373/MetaIRNet"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/selective-sampling-for-accelerating-training-1","slug":"selective-sampling-for-accelerating-training-1","title":"Selective sampling for accelerating training of deep neural networks","date":"2019-11-16","arxiv_id":"1911.06996","repositories_listed":1,"syntology":null},{"url":"/paper/deepsat-v2-feature-augmented-convolutional","slug":"deepsat-v2-feature-augmented-convolutional","title":"DeepSat V2: Feature Augmented Convolutional Neural Nets for Satellite Image Classification","date":"2019-11-15","arxiv_id":"1911.07747","repositories_listed":1,"syntology":null},{"url":"/paper/in-domain-representation-learning-for-remote-1","slug":"in-domain-representation-learning-for-remote-1","title":"In-domain representation learning for remote sensing","date":"2019-11-15","arxiv_id":"1911.06721","repositories_listed":1,"syntology":null},{"url":"/paper/simple-iterative-method-for-generating","slug":"simple-iterative-method-for-generating","title":"Simple iterative method for generating targeted universal adversarial perturbations","date":"2019-11-15","arxiv_id":"1911.06502","repositories_listed":1,"syntology":null},{"url":"/paper/a-computing-kernel-for-network-binarization","slug":"a-computing-kernel-for-network-binarization","title":"A Computing Kernel for Network Binarization on PyTorch","date":"2019-11-11","arxiv_id":"1911.04477","repositories_listed":1,"syntology":null},{"url":"/paper/learning-from-brains-how-to-regularize-1","slug":"learning-from-brains-how-to-regularize-1","title":"Learning From Brains How to Regularize Machines","date":"2019-11-11","arxiv_id":"1911.05072","repositories_listed":1,"syntology":null},{"url":"/paper/meta-label-correction-for-learning-with-weak-1","slug":"meta-label-correction-for-learning-with-weak-1","title":"Meta Label Correction for Noisy Label Learning","date":"2019-11-10","arxiv_id":"1911.03809","repositories_listed":1,"syntology":{"n":11,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/meta-label-correction-for-learning-with-weak-1#ran","syntology_url":"https://syntology.ai/paper/1911.03809","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03809"}},"official":{"repos":["microsoft/mlc"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-design-of-convolutional-neural","slug":"on-the-design-of-convolutional-neural","title":"On the design of convolutional neural networks for automatic detection of Alzheimer's disease","date":"2019-11-09","arxiv_id":"1911.03740","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-relationship-between-self-attention-1","slug":"on-the-relationship-between-self-attention-1","title":"On the Relationship between Self-Attention and Convolutional Layers","date":"2019-11-08","arxiv_id":"1911.03584","repositories_listed":1,"syntology":{"n":16,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":3,"n_honours":1,"n_violates":0,"n_no_contract":9,"n_pointer_only":4,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/on-the-relationship-between-self-attention-1#ran","syntology_url":"https://syntology.ai/paper/1911.03584","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.03584"}},"official":{"repos":["epfml/attention-cnn"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/a-programmable-approach-to-model-compression","slug":"a-programmable-approach-to-model-compression","title":"A Programmable Approach to Neural Network Compression","date":"2019-11-06","arxiv_id":"1911.02497","repositories_listed":1,"syntology":null},{"url":"/paper/hyperspectral-image-classification-via-sparse","slug":"hyperspectral-image-classification-via-sparse","title":"Hyperspectral Image Classification via Sparse Representation With Incremental Dictionaries","date":"2019-11-06","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/test-metrics-for-recurrent-neural-networks","slug":"test-metrics-for-recurrent-neural-networks","title":"Coverage Guided Testing for Recurrent Neural Networks","date":"2019-11-05","arxiv_id":"1911.01952","repositories_listed":1,"syntology":null},{"url":"/paper/an-algorithm-for-routing-capsules-in-all","slug":"an-algorithm-for-routing-capsules-in-all","title":"An Algorithm for Routing Capsules in All Domains","date":"2019-11-02","arxiv_id":"1911.00792","repositories_listed":1,"syntology":null},{"url":"/paper/deep-metric-learning-based-feature-embedding","slug":"deep-metric-learning-based-feature-embedding","title":"Deep Metric Learning-Based Feature Embedding for Hyperspectral Image Classification","date":"2019-10-30","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/scalable-deep-neural-networks-via-low-rank-1","slug":"scalable-deep-neural-networks-via-low-rank-1","title":"Decomposable-Net: Scalable Low-Rank Compression for Neural Networks","date":"2019-10-29","arxiv_id":"1910.13141","repositories_listed":1,"syntology":null},{"url":"/paper/shoestring-graph-based-semi-supervised","slug":"shoestring-graph-based-semi-supervised","title":"Shoestring: Graph-Based Semi-Supervised Learning with Severely Limited Labeled Data","date":"2019-10-28","arxiv_id":"1910.12976","repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-active-learning-system-for-species","slug":"a-deep-active-learning-system-for-species","title":"A deep active learning system for species identification and counting in camera trap images","date":"2019-10-22","arxiv_id":"1910.09716","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-deep-active-learning-system-for-species#ran","syntology_url":"https://syntology.ai/paper/1910.09716","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.09716"}},"official":null}},{"url":"/paper/improving-singing-voice-separation-with-the","slug":"improving-singing-voice-separation-with-the","title":"Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical Energy","date":"2019-10-22","arxiv_id":"1910.10071","repositories_listed":1,"syntology":null},{"url":"/paper/improving-the-gating-mechanism-of-recurrent-1","slug":"improving-the-gating-mechanism-of-recurrent-1","title":"Improving the Gating Mechanism of Recurrent Neural Networks","date":"2019-10-22","arxiv_id":"1910.09890","repositories_listed":1,"syntology":null},{"url":"/paper/kernel-computations-from-large-scale-random","slug":"kernel-computations-from-large-scale-random","title":"Kernel computations from large-scale random features obtained by Optical Processing Units","date":"2019-10-22","arxiv_id":"1910.09880","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-inductive-bias-of-neural-networks","slug":"leveraging-inductive-bias-of-neural-networks","title":"Image recognition from raw labels collected without annotators","date":"2019-10-20","arxiv_id":"1910.09055","repositories_listed":1,"syntology":null},{"url":"/paper/toward-metrics-for-differentiating-out-of","slug":"toward-metrics-for-differentiating-out-of","title":"Toward Metrics for Differentiating Out-of-Distribution Sets","date":"2019-10-18","arxiv_id":"1910.08650","repositories_listed":1,"syntology":null},{"url":"/paper/effect-of-superpixel-aggregation-on","slug":"effect-of-superpixel-aggregation-on","title":"Effect of Superpixel Aggregation on Explanations in LIME -- A Case Study with Biological Data","date":"2019-10-17","arxiv_id":"1910.07856","repositories_listed":1,"syntology":null},{"url":"/paper/deepsearch-simple-and-effective-blackbox","slug":"deepsearch-simple-and-effective-blackbox","title":"DeepSearch: A Simple and Effective Blackbox Attack for Deep Neural Networks","date":"2019-10-14","arxiv_id":"1910.06296","repositories_listed":1,"syntology":null},{"url":"/paper/scale-equivariant-steerable-networks-1","slug":"scale-equivariant-steerable-networks-1","title":"Scale-Equivariant Steerable Networks","date":"2019-10-14","arxiv_id":"1910.11093","repositories_listed":1,"syntology":{"n":8,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":5,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","sample_list":"/paper/scale-equivariant-steerable-networks-1#ran","syntology_url":"https://syntology.ai/paper/1910.11093","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.11093"}},"official":null}},{"url":"/paper/generative-image-translation-for-data-1","slug":"generative-image-translation-for-data-1","title":"Generative Image Translation for Data Augmentation in Colorectal Histopathology Images","date":"2019-10-13","arxiv_id":"1910.05827","repositories_listed":1,"syntology":null},{"url":"/paper/context-gated-convolution","slug":"context-gated-convolution","title":"Context-Gated Convolution","date":"2019-10-12","arxiv_id":"1910.05577","repositories_listed":1,"syntology":null},{"url":"/paper/cross-domain-image-classification-through","slug":"cross-domain-image-classification-through","title":"Cross-Domain Image Classification through Neural-Style Transfer Data Augmentation","date":"2019-10-12","arxiv_id":"1910.05611","repositories_listed":1,"syntology":null},{"url":"/paper/drop-to-adapt-learning-discriminative","slug":"drop-to-adapt-learning-discriminative","title":"Drop to Adapt: Learning Discriminative Features for Unsupervised Domain Adaptation","date":"2019-10-12","arxiv_id":"1910.05562","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-adequacy-of-untuned-warmup-for","slug":"on-the-adequacy-of-untuned-warmup-for","title":"On the adequacy of untuned warmup for adaptive optimization","date":"2019-10-09","arxiv_id":"1910.04209","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-the-adequacy-of-untuned-warmup-for#ran","syntology_url":"https://syntology.ai/paper/1910.04209","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.04209"}},"official":null}},{"url":"/paper/dynamic-mode-decomposition-based-feature-for","slug":"dynamic-mode-decomposition-based-feature-for","title":"Dynamic Mode Decomposition based feature for Image Classification","date":"2019-10-08","arxiv_id":"1910.03188","repositories_listed":1,"syntology":null},{"url":"/paper/lossy-image-compression-with-recurrent-neural","slug":"lossy-image-compression-with-recurrent-neural","title":"Observer Dependent Lossy Image Compression","date":"2019-10-08","arxiv_id":"1910.03472","repositories_listed":1,"syntology":null},{"url":"/paper/deep-neural-network-compression-for-image","slug":"deep-neural-network-compression-for-image","title":"Deep Neural Network Compression for Image Classification and Object Detection","date":"2019-10-07","arxiv_id":"1910.02747","repositories_listed":1,"syntology":null},{"url":"/paper/generating-relevant-counter-examples-from-a","slug":"generating-relevant-counter-examples-from-a","title":"Generating Relevant Counter-Examples from a Positive Unlabeled Dataset for Image Classification","date":"2019-10-04","arxiv_id":"1910.01968","repositories_listed":1,"syntology":null},{"url":"/paper/tensor-based-algorithms-for-image","slug":"tensor-based-algorithms-for-image","title":"Tensor-based algorithms for image classification","date":"2019-10-04","arxiv_id":"1910.02150","repositories_listed":1,"syntology":null},{"url":"/paper/robust-few-shot-learning-with-adversarially-1","slug":"robust-few-shot-learning-with-adversarially-1","title":"Adversarially Robust Few-Shot Learning: A Meta-Learning Approach","date":"2019-10-02","arxiv_id":"1910.00982","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/robust-few-shot-learning-with-adversarially-1#ran","syntology_url":"https://syntology.ai/paper/1910.00982","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.00982"}},"official":{"repos":["goldblum/AdversarialQuerying"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/w-net-a-cnn-based-architecture-for-white","slug":"w-net-a-cnn-based-architecture-for-white","title":"W-Net: A CNN-based Architecture for White Blood Cells Image Classification","date":"2019-10-02","arxiv_id":"1910.01091","repositories_listed":1,"syntology":null},{"url":"/paper/addressing-failure-prediction-by-learning","slug":"addressing-failure-prediction-by-learning","title":"Addressing Failure Prediction by Learning Model Confidence","date":"2019-10-01","arxiv_id":"1910.04851","repositories_listed":1,"syntology":null},{"url":"/paper/danet-divergent-activation-for-weakly","slug":"danet-divergent-activation-for-weakly","title":"DANet: Divergent Activation for Weakly Supervised Object Localization","date":"2019-10-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-model-interpretability-and","slug":"leveraging-model-interpretability-and","title":"Leveraging Model Interpretability and Stability to increase Model Robustness","date":"2019-10-01","arxiv_id":"1910.00387","repositories_listed":1,"syntology":null},{"url":"/paper/meta-learning-algorithms-for-few-shot","slug":"meta-learning-algorithms-for-few-shot","title":"Meta-learning algorithms for Few-Shot Computer Vision","date":"2019-09-30","arxiv_id":"1909.13579","repositories_listed":1,"syntology":null},{"url":"/paper/xnor-net-improved-binary-neural-networks","slug":"xnor-net-improved-binary-neural-networks","title":"XNOR-Net++: Improved Binary Neural Networks","date":"2019-09-30","arxiv_id":"1909.13863","repositories_listed":1,"syntology":null},{"url":"/paper/pixel-wise-polsar-image-classification-via-a","slug":"pixel-wise-polsar-image-classification-via-a","title":"Pixel-Wise PolSAR Image Classification via a Novel Complex-Valued Deep Fully Convolutional Network","date":"2019-09-29","arxiv_id":"1909.13299","repositories_listed":1,"syntology":null},{"url":"/paper/unsharp-masking-layer-injecting-prior","slug":"unsharp-masking-layer-injecting-prior","title":"Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image Classification","date":"2019-09-29","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/genetic-programming-and-gradient-descent-a","slug":"genetic-programming-and-gradient-descent-a","title":"Genetic Programming and Gradient Descent: A Memetic Approach to Binary Image Classification","date":"2019-09-28","arxiv_id":"1909.13030","repositories_listed":1,"syntology":null},{"url":"/paper/learning-in-confusion-batch-active-learning","slug":"learning-in-confusion-batch-active-learning","title":"Noisy Batch Active Learning with Deterministic Annealing","date":"2019-09-27","arxiv_id":"1909.12473","repositories_listed":1,"syntology":null},{"url":"/paper/urban-sound-tagging-using-convolutional","slug":"urban-sound-tagging-using-convolutional","title":"Urban Sound Tagging using Convolutional Neural Networks","date":"2019-09-27","arxiv_id":"1909.12699","repositories_listed":1,"syntology":null},{"url":"/paper/balanced-binary-neural-networks-with-gated","slug":"balanced-binary-neural-networks-with-gated","title":"Balanced Binary Neural Networks with Gated Residual","date":"2019-09-26","arxiv_id":"1909.12117","repositories_listed":1,"syntology":null},{"url":"/paper/two-stage-image-classification-supervised-by","slug":"two-stage-image-classification-supervised-by","title":"Two-stage Image Classification Supervised by a Single Teacher Single Student Model","date":"2019-09-26","arxiv_id":"1909.12111","repositories_listed":1,"syntology":null},{"url":"/paper/improving-confident-classifiers-for-out-of","slug":"improving-confident-classifiers-for-out-of","title":"Improving Confident-Classifiers For Out-of-distribution Detection","date":"2019-09-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/manifold-forests-closing-the-gap-on-neural","slug":"manifold-forests-closing-the-gap-on-neural","title":"Manifold Oblique Random Forests: Towards Closing the Gap on Convolutional Deep Networks","date":"2019-09-25","arxiv_id":"1909.11799","repositories_listed":1,"syntology":null},{"url":"/paper/anchor-loss-modulating-loss-scale-based-on","slug":"anchor-loss-modulating-loss-scale-based-on","title":"Anchor Loss: Modulating Loss Scale based on Prediction Difficulty","date":"2019-09-24","arxiv_id":"1909.11155","repositories_listed":1,"syntology":null},{"url":"/paper/polsar-image-classification-based-on-dilated","slug":"polsar-image-classification-based-on-dilated","title":"PolSAR Image Classification Based on Dilated Convolution and Pixel-Refining Parallel Mapping network in the Complex Domain","date":"2019-09-24","arxiv_id":"1909.10783","repositories_listed":1,"syntology":null},{"url":"/paper/190909656","slug":"190909656","title":"Understanding and Robustifying Differentiable Architecture Search","date":"2019-09-20","arxiv_id":"1909.09656","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":1,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/190909656#ran","syntology_url":"https://syntology.ai/paper/1909.09656","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.09656"}},"official":{"repos":["automl/RobustDARTS"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/understanding-architectures-learnt-by-cell","slug":"understanding-architectures-learnt-by-cell","title":"Understanding Architectures Learnt by Cell-based Neural Architecture Search","date":"2019-09-20","arxiv_id":"1909.09569","repositories_listed":1,"syntology":null},{"url":"/paper/timage-a-robust-time-series-classification","slug":"timage-a-robust-time-series-classification","title":"Timage -- A Robust Time Series Classification Pipeline","date":"2019-09-19","arxiv_id":"1909.09149","repositories_listed":1,"syntology":null},{"url":"/paper/transfer-learning-with-dynamic-distribution","slug":"transfer-learning-with-dynamic-distribution","title":"Transfer Learning with Dynamic Distribution Adaptation","date":"2019-09-17","arxiv_id":"1909.08531","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-investigation-of-randomized","slug":"an-empirical-investigation-of-randomized","title":"An Empirical Investigation of Randomized Defenses against Adversarial Attacks","date":"2019-09-12","arxiv_id":"1909.05580","repositories_listed":1,"syntology":null},{"url":"/paper/hhhfl-hierarchical-heterogeneous-horizontal","slug":"hhhfl-hierarchical-heterogeneous-horizontal","title":"HHHFL: Hierarchical Heterogeneous Horizontal Federated Learning for Electroencephalography","date":"2019-09-11","arxiv_id":"1909.05784","repositories_listed":1,"syntology":null},{"url":"/paper/fda-feature-disruptive-attack","slug":"fda-feature-disruptive-attack","title":"FDA: Feature Disruptive Attack","date":"2019-09-10","arxiv_id":"1909.04385","repositories_listed":1,"syntology":null},{"url":"/paper/3d-u2-net-a-3d-universal-u-net-for-multi","slug":"3d-u2-net-a-3d-universal-u-net-for-multi","title":"3D U$^2$-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation","date":"2019-09-04","arxiv_id":"1909.06012","repositories_listed":1,"syntology":null},{"url":"/paper/lit-learned-intermediate-representation","slug":"lit-learned-intermediate-representation","title":"LIT: Learned Intermediate Representation Training for Model Compression","date":"2019-09-04","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/detecting-floodwater-on-roadways-from-image","slug":"detecting-floodwater-on-roadways-from-image","title":"Detecting floodwater on roadways from image data with handcrafted features and deep transfer learning","date":"2019-08-31","arxiv_id":"1909.00125","repositories_listed":1,"syntology":null},{"url":"/paper/gated-convolutional-networks-with-hybrid","slug":"gated-convolutional-networks-with-hybrid","title":"Gated Convolutional Networks with Hybrid Connectivity for Image Classification","date":"2019-08-26","arxiv_id":"1908.09699","repositories_listed":1,"syntology":{"n":5,"n_ran":4,"n_constructed":0,"n_ran_checked":0,"n_instrument":4,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":5,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/gated-convolutional-networks-with-hybrid#ran","syntology_url":"https://syntology.ai/paper/1908.09699","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.09699"}},"official":{"repos":["winycg/HCGNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/calibration-of-deep-probabilistic-models-with","slug":"calibration-of-deep-probabilistic-models-with","title":"Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks","date":"2019-08-23","arxiv_id":"1908.08972","repositories_listed":1,"syntology":null},{"url":"/paper/colornet-estimating-colorfulness-in-natural","slug":"colornet-estimating-colorfulness-in-natural","title":"ColorNet -- Estimating Colorfulness in Natural Images","date":"2019-08-22","arxiv_id":"1908.08505","repositories_listed":1,"syntology":null},{"url":"/paper/190807899","slug":"190807899","title":"Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples","date":"2019-08-21","arxiv_id":"1908.07899","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-defense-by-suppressing-high","slug":"adversarial-defense-by-suppressing-high","title":"Adversarial Defense by Suppressing High-frequency Components","date":"2019-08-19","arxiv_id":"1908.06566","repositories_listed":1,"syntology":null},{"url":"/paper/dynamic-graph-message-passing-networks","slug":"dynamic-graph-message-passing-networks","title":"Dynamic Graph Message Passing Networks","date":"2019-08-19","arxiv_id":"1908.06955","repositories_listed":1,"syntology":null},{"url":"/paper/nlnl-negative-learning-for-noisy-labels","slug":"nlnl-negative-learning-for-noisy-labels","title":"NLNL: Negative Learning for Noisy Labels","date":"2019-08-19","arxiv_id":"1908.07387","repositories_listed":1,"syntology":null},{"url":"/paper/demystifying-learning-rate-polices-for-high","slug":"demystifying-learning-rate-polices-for-high","title":"Demystifying Learning Rate Policies for High Accuracy Training of Deep Neural Networks","date":"2019-08-18","arxiv_id":"1908.06477","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/demystifying-learning-rate-polices-for-high#ran","syntology_url":"https://syntology.ai/paper/1908.06477","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.06477"}},"official":{"repos":["git-disl/LRBench"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/needles-in-haystacks-on-classifying-tiny","slug":"needles-in-haystacks-on-classifying-tiny","title":"Needles in Haystacks: On Classifying Tiny Objects in Large Images","date":"2019-08-16","arxiv_id":"1908.06037","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/needles-in-haystacks-on-classifying-tiny#ran","syntology_url":"https://syntology.ai/paper/1908.06037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.06037"}},"official":{"repos":["facebookresearch/Needles-in-Haystacks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/scarletnas-bridging-the-gap-between","slug":"scarletnas-bridging-the-gap-between","title":"SCARLET-NAS: Bridging the Gap between Stability and Scalability in Weight-sharing Neural Architecture Search","date":"2019-08-16","arxiv_id":"1908.06022","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-bayesian-approach-for-metric-learning","slug":"sparse-bayesian-approach-for-metric-learning","title":"Sparse Bayesian approach for metric learning in latent space","date":"2019-08-15","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/neural-plasticity-networks","slug":"neural-plasticity-networks","title":"Neural Plasticity Networks","date":"2019-08-13","arxiv_id":"1908.08118","repositories_listed":1,"syntology":null},{"url":"/paper/lip-local-importance-based-pooling","slug":"lip-local-importance-based-pooling","title":"LIP: Local Importance-based Pooling","date":"2019-08-12","arxiv_id":"1908.04156","repositories_listed":1,"syntology":null},{"url":"/paper/recent-advances-in-deep-learning-for-object","slug":"recent-advances-in-deep-learning-for-object","title":"Recent Advances in Deep Learning for Object Detection","date":"2019-08-10","arxiv_id":"1908.03673","repositories_listed":1,"syntology":null},{"url":"/paper/neural-image-compression-and-explanation","slug":"neural-image-compression-and-explanation","title":"Neural Image Compression and Explanation","date":"2019-08-09","arxiv_id":"1908.08988","repositories_listed":1,"syntology":null},{"url":"/paper/progressive-transfer-learning-for-person-re","slug":"progressive-transfer-learning-for-person-re","title":"Progressive Transfer Learning","date":"2019-08-07","arxiv_id":"1908.02492","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-convolutional-neural-networks","slug":"explaining-convolutional-neural-networks","title":"Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation","date":"2019-08-06","arxiv_id":"1908.04351","repositories_listed":1,"syntology":null},{"url":"/paper/squeezenas-fast-neural-architecture-search","slug":"squeezenas-fast-neural-architecture-search","title":"SqueezeNAS: Fast neural architecture search for faster semantic segmentation","date":"2019-08-05","arxiv_id":"1908.01748","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/squeezenas-fast-neural-architecture-search#ran","syntology_url":"https://syntology.ai/paper/1908.01748","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.01748"}},"official":null}},{"url":"/paper/seeing-is-not-believing-camouflage-attacks-on","slug":"seeing-is-not-believing-camouflage-attacks-on","title":"Seeing is Not Believing: Camouflage Attacks on Image Scaling Algorithms","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/icartoonface-a-benchmark-of-cartoon-person","slug":"icartoonface-a-benchmark-of-cartoon-person","title":"Cartoon Face Recognition: A Benchmark Dataset","date":"2019-07-31","arxiv_id":"1907.13394","repositories_listed":1,"syntology":null},{"url":"/paper/open-set-domain-adaptation-for-image-and","slug":"open-set-domain-adaptation-for-image-and","title":"Open Set Domain Adaptation for Image and Action Recognition","date":"2019-07-30","arxiv_id":"1907.12865","repositories_listed":1,"syntology":{"n":7,"n_ran":4,"n_constructed":0,"n_ran_checked":2,"n_instrument":2,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/open-set-domain-adaptation-for-image-and#ran","syntology_url":"https://syntology.ai/paper/1907.12865","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.12865"}},"official":{"repos":["Heliot7/open-set-da"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/forced-spatial-attention-for-driver-foot","slug":"forced-spatial-attention-for-driver-foot","title":"Forced Spatial Attention for Driver Foot Activity Classification","date":"2019-07-27","arxiv_id":"1907.11824","repositories_listed":1,"syntology":null},{"url":"/paper/on-the-design-of-black-box-adversarial","slug":"on-the-design-of-black-box-adversarial","title":"On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method","date":"2019-07-26","arxiv_id":"1907.11684","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/on-the-design-of-black-box-adversarial#ran","syntology_url":"https://syntology.ai/paper/1907.11684","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.11684"}},"official":{"repos":["LinLabNEU/Blackbox_ADMM"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/invariance-reduces-variance-understanding","slug":"invariance-reduces-variance-understanding","title":"A Group-Theoretic Framework for Data Augmentation","date":"2019-07-25","arxiv_id":"1907.10905","repositories_listed":1,"syntology":null},{"url":"/paper/multidepth-single-image-depth-estimation-via","slug":"multidepth-single-image-depth-estimation-via","title":"MultiDepth: Single-Image Depth Estimation via Multi-Task Regression and Classification","date":"2019-07-25","arxiv_id":"1907.11111","repositories_listed":1,"syntology":null},{"url":"/paper/compact-global-descriptor-for-neural-networks","slug":"compact-global-descriptor-for-neural-networks","title":"Compact Global Descriptor for Neural Networks","date":"2019-07-23","arxiv_id":"1907.09665","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-correlation-tracking-via-joint","slug":"real-time-correlation-tracking-via-joint","title":"Real-Time Correlation Tracking via Joint Model Compression and Transfer","date":"2019-07-23","arxiv_id":"1907.09831","repositories_listed":1,"syntology":null},{"url":"/paper/image-classification-with-hierarchical","slug":"image-classification-with-hierarchical","title":"Image Classification with Hierarchical Multigraph Networks","date":"2019-07-21","arxiv_id":"1907.09000","repositories_listed":1,"syntology":null},{"url":"/paper/subspace-inference-for-bayesian-deep-learning","slug":"subspace-inference-for-bayesian-deep-learning","title":"Subspace Inference for Bayesian Deep Learning","date":"2019-07-17","arxiv_id":"1907.07504","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/subspace-inference-for-bayesian-deep-learning#ran","syntology_url":"https://syntology.ai/paper/1907.07504","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1907.07504"}},"official":{"repos":["wjmaddox/drbayes"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/relation-network-for-multi-label-aerial-image","slug":"relation-network-for-multi-label-aerial-image","title":"Relation Network for Multi-label Aerial Image Classification","date":"2019-07-16","arxiv_id":"1907.07274","repositories_listed":1,"syntology":null}],"record_sha256":"065d1382878a1d1c07f8d02c9949cd742d2f9aa426f2b870652f13ff3bd07a2b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}