{"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":"/method/softmax/papers/366","list_of":"/method/softmax","method":"Softmax","archive":{"snapshot":"2025-07-28"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"date (newest first), then slug","page":366,"pages_in_order":375,"rows_per_page":100,"rows":[36501,36600],"of":37443,"counts":{"archive_papers_tagged":37443,"with_a_code_link":15869,"where_syntology_ran_a_sample":4578,"not_listed_spam_title":0,"listed":37443,"listed_where_code_ran":4578,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3835,"every_run_a_failure_of_syntologys_instrument":743,"listed_with_a_run_with_no_instrument_failure":3835,"listed_every_run_a_failure_of_syntologys_instrument":743,"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":"/method/softmax","prev":"/method/softmax/papers/365","next":"/method/softmax/papers/367","papers":[{"paper":"/paper/segmenting-unknown-3d-objects-from-real-depth","slug":"segmenting-unknown-3d-objects-from-real-depth","title":"Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data","date":"2018-09-16","arxiv_id":"1809.05825","n_code_links":4,"syntology":null},{"paper":"/paper/graph-convolutional-networks-based-word","slug":"graph-convolutional-networks-based-word","title":"Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks","date":"2018-09-12","arxiv_id":"1809.04283","n_code_links":1,"syntology":null},{"paper":"/paper/music-transformer","slug":"music-transformer","title":"Music Transformer","date":"2018-09-12","arxiv_id":"1809.04281","n_code_links":12,"syntology":{"ran":3,"of":4,"n_ran_checked":3,"n_instrument":0,"unverified":1,"pointer_only":2,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"discovering-low-precision-networks-close-to","title":"Discovering Low-Precision Networks Close to Full-Precision Networks for Efficient Embedded Inference","date":"2018-09-11","arxiv_id":"1809.04191","n_code_links":0,"syntology":null},{"paper":"/paper/heated-up-softmax-embedding","slug":"heated-up-softmax-embedding","title":"Heated-Up Softmax Embedding","date":"2018-09-11","arxiv_id":"1809.04157","n_code_links":1,"syntology":{"ran":6,"of":10,"n_ran_checked":6,"n_instrument":0,"unverified":4,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","official":{"repos":["ColumbiaDVMM/Heated_Up_Softmax_Embedding"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"on-the-alignment-problem-in-multi-head","title":"On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translation","date":"2018-09-11","arxiv_id":"1809.03985","n_code_links":0,"syntology":null},{"paper":null,"slug":"parallel-separable-3d-convolution-for-video","title":"Parallel Separable 3D Convolution for Video and Volumetric Data Understanding","date":"2018-09-11","arxiv_id":"1809.04096","n_code_links":0,"syntology":null},{"paper":null,"slug":"interactive-binary-image-segmentation-with","title":"Interactive Binary Image Segmentation with Edge Preservation","date":"2018-09-10","arxiv_id":"1809.03334","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-zoom-a-saliency-based-sampling","slug":"learning-to-zoom-a-saliency-based-sampling","title":"Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks","date":"2018-09-10","arxiv_id":"1809.03355","n_code_links":1,"syntology":null},{"paper":null,"slug":"towards-one-shot-learning-for-rare-word","title":"Towards one-shot learning for rare-word translation with external experts","date":"2018-09-10","arxiv_id":"1809.03182","n_code_links":0,"syntology":null},{"paper":null,"slug":"fingertip-detection-and-tracking-for","title":"Fingertip Detection and Tracking for Recognition of Air-Writing in Videos","date":"2018-09-09","arxiv_id":"1809.03016","n_code_links":0,"syntology":null},{"paper":null,"slug":"convolutional-neural-network-text","title":"Convolutional Neural Network: Text Classification Model for Open Domain Question Answering System","date":"2018-09-07","arxiv_id":"1809.02479","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-allocentric-intuitive-physics","title":"Neural Allocentric Intuitive Physics Prediction from Real Videos","date":"2018-09-07","arxiv_id":"1809.03330","n_code_links":0,"syntology":null},{"paper":null,"slug":"character-aware-decoder-for-neural-machine","title":"Character-Aware Decoder for Translation into Morphologically Rich Languages","date":"2018-09-06","arxiv_id":"1809.02223","n_code_links":0,"syntology":null},{"paper":"/paper/effective-deep-learning-for-semantic","slug":"effective-deep-learning-for-semantic","title":"Effective Deep Learning for Semantic Segmentation Based Bleeding Zone Detection in Capsule Endoscopy Images","date":"2018-09-06","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/panoptic-segmentation-with-a-joint-semantic","slug":"panoptic-segmentation-with-a-joint-semantic","title":"Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network","date":"2018-09-06","arxiv_id":"1809.02110","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-is-contrast-encoded-in-deep-neural","title":"How is Contrast Encoded in Deep Neural Networks?","date":"2018-09-05","arxiv_id":"1809.01438","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-neural-network-aided-approach-for-ldpc","title":"A Neural Network Aided Approach for LDPC Coded DCO-OFDM with Clipping Distortion","date":"2018-09-04","arxiv_id":"1809.01022","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-efficient-approach-for-polyps-detection-in","title":"An Efficient Approach for Polyps Detection in Endoscopic Videos Based on Faster R-CNN","date":"2018-09-04","arxiv_id":"1809.01263","n_code_links":0,"syntology":null},{"paper":"/paper/towards-automated-customer-support","slug":"towards-automated-customer-support","title":"Towards Automated Customer Support","date":"2018-09-02","arxiv_id":"1809.00303","n_code_links":1,"syntology":null},{"paper":"/paper/associating-inter-image-salient-instances-for","slug":"associating-inter-image-salient-instances-for","title":"Associating Inter-Image Salient Instances for Weakly Supervised Semantic Segmentation","date":"2018-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"beyond-error-propagation-in-neural-machine","title":"Beyond Error Propagation in Neural Machine Translation: Characteristics of Language Also Matter","date":"2018-09-01","arxiv_id":"1809.00120","n_code_links":0,"syntology":null},{"paper":"/paper/constrained-optimization-based-low-rank","slug":"constrained-optimization-based-low-rank","title":"Constrained Optimization Based Low-Rank Approximation of Deep Neural Networks","date":"2018-09-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"detnet-design-backbone-for-object-detection","title":"DetNet: Design Backbone for Object Detection","date":"2018-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"dft-based-transformation-invariant-pooling","title":"DFT-based Transformation Invariant Pooling Layer for Visual Classification","date":"2018-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/esrgan-enhanced-super-resolution-generative","slug":"esrgan-enhanced-super-resolution-generative","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","date":"2018-09-01","arxiv_id":"1809.00219","n_code_links":46,"syntology":{"ran":33,"of":44,"n_ran_checked":29,"n_instrument":4,"unverified":11,"pointer_only":7,"phrase":"33 ran (of which 0 constructed an object rather than computing a result; 29 with no instrument failure: 0 honoured, 0 violated, 29 with no contract checked; 4 where Syntology's instrument failed) · 11 unverified","official":{"repos":["xinntao/ESRGAN"],"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":["listed","official"]}}},{"paper":"/paper/generative-adversarial-network-with-spatial","slug":"generative-adversarial-network-with-spatial","title":"Generative Adversarial Network with Spatial Attention for Face Attribute Editing","date":"2018-09-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/learning-efficient-single-stage-pedestrian","slug":"learning-efficient-single-stage-pedestrian","title":"Learning Efficient Single-stage Pedestrian Detectors by Asymptotic Localization Fitting","date":"2018-09-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-low-precision-deep-neural-networks","title":"Learning Sparse Low-Precision Neural Networks With Learnable Regularization","date":"2018-09-01","arxiv_id":"1809.00095","n_code_links":0,"syntology":null},{"paper":"/paper/parameter-sharing-methods-for-multilingual","slug":"parameter-sharing-methods-for-multilingual","title":"Parameter Sharing Methods for Multilingual Self-Attentional Translation Models","date":"2018-09-01","arxiv_id":"1809.00252","n_code_links":1,"syntology":null},{"paper":null,"slug":"spatio-temporal-transformer-network-for-video","title":"Spatio-temporal Transformer Network for Video Restoration","date":"2018-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/tbn-convolutional-neural-network-with-ternary","slug":"tbn-convolutional-neural-network-with-ternary","title":"TBN: Convolutional Neural Network with Ternary Inputs and Binary Weights","date":"2018-09-01","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":null,"slug":"training-binary-weight-networks-via-semi","title":"Training Binary Weight Networks via Semi-Binary Decomposition","date":"2018-09-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"cognate-aware-morphological-segmentation-for","title":"Cognate-aware morphological segmentation for multilingual neural translation","date":"2018-08-31","arxiv_id":"1808.10791","n_code_links":0,"syntology":null},{"paper":null,"slug":"juncnet-a-deep-neural-network-for-road","title":"JuncNet: A Deep Neural Network for Road Junction Disambiguation for Autonomous Vehicles","date":"2018-08-31","arxiv_id":"1809.01011","n_code_links":0,"syntology":null},{"paper":null,"slug":"self-attention-linguistic-acoustic-decoder","title":"Self-Attention Linguistic-Acoustic Decoder","date":"2018-08-31","arxiv_id":"1808.10678","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-memad-submission-to-the-wmt18-multimodal","title":"The MeMAD Submission to the WMT18 Multimodal Translation Task","date":"2018-08-31","arxiv_id":"1808.10802","n_code_links":0,"syntology":null},{"paper":null,"slug":"the-impact-of-preprocessing-on-deep","title":"The Impact of Preprocessing on Deep Representations for Iris Recognition on Unconstrained Environments","date":"2018-08-29","arxiv_id":"1808.10032","n_code_links":0,"syntology":null},{"paper":null,"slug":"towards-semi-supervised-learning-for-deep","title":"Towards Semi-Supervised Learning for Deep Semantic Role Labeling","date":"2018-08-28","arxiv_id":"1808.09543","n_code_links":0,"syntology":null},{"paper":"/paper/iiidyt-at-iest-2018-implicit-emotion","slug":"iiidyt-at-iest-2018-implicit-emotion","title":"IIIDYT at IEST 2018: Implicit Emotion Classification With Deep Contextualized Word Representations","date":"2018-08-27","arxiv_id":"1808.08672","n_code_links":1,"syntology":null},{"paper":"/paper/wide-activation-for-efficient-and-accurate","slug":"wide-activation-for-efficient-and-accurate","title":"Wide Activation for Efficient and Accurate Image Super-Resolution","date":"2018-08-27","arxiv_id":"1808.08718","n_code_links":12,"syntology":{"ran":9,"of":17,"n_ran_checked":9,"n_instrument":0,"unverified":8,"pointer_only":2,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified","official":{"repos":["JiahuiYu/wdsr_ntire2018"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/semi-autoregressive-neural-machine","slug":"semi-autoregressive-neural-machine","title":"Semi-Autoregressive Neural Machine Translation","date":"2018-08-26","arxiv_id":"1808.08583","n_code_links":1,"syntology":{"ran":1,"of":4,"n_ran_checked":1,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["chqiwang/sa-nmt"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"spectral-pruning-compressing-deep-neural","title":"Spectral Pruning: Compressing Deep Neural Networks via Spectral Analysis and its Generalization Error","date":"2018-08-26","arxiv_id":"1808.08558","n_code_links":0,"syntology":null},{"paper":null,"slug":"how-many-labeled-license-plates-are-needed","title":"How many labeled license plates are needed?","date":"2018-08-25","arxiv_id":"1808.08410","n_code_links":0,"syntology":null},{"paper":null,"slug":"atherosclerotic-carotid-plaques-on-panoramic","title":"Atherosclerotic carotid plaques on panoramic imaging: an automatic detection using deep learning with small dataset","date":"2018-08-24","arxiv_id":"1808.08093","n_code_links":0,"syntology":null},{"paper":null,"slug":"paranet-using-dense-blocks-for-early","title":"ParaNet - Using Dense Blocks for Early Inference","date":"2018-08-24","arxiv_id":"1808.08308","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-shared-structures-and-hierarchies","title":"Exploring Shared Structures and Hierarchies for Multiple NLP Tasks","date":"2018-08-23","arxiv_id":"1808.07658","n_code_links":0,"syntology":null},{"paper":"/paper/revisiting-the-importance-of-encoding-logic","slug":"revisiting-the-importance-of-encoding-logic","title":"Revisiting the Importance of Encoding Logic Rules in Sentiment Classification","date":"2018-08-23","arxiv_id":"1808.07733","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-survey-of-modern-object-detection","title":"A Survey of Modern Object Detection Literature using Deep Learning","date":"2018-08-22","arxiv_id":"1808.07256","n_code_links":0,"syntology":null},{"paper":"/paper/attention-gated-networks-learning-to-leverage","slug":"attention-gated-networks-learning-to-leverage","title":"Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images","date":"2018-08-22","arxiv_id":"1808.08114","n_code_links":2,"syntology":null},{"paper":null,"slug":"improving-matching-models-with-contextualized","title":"Improving Matching Models with Hierarchical Contextualized Representations for Multi-turn Response Selection","date":"2018-08-22","arxiv_id":"1808.07244","n_code_links":0,"syntology":null},{"paper":"/paper/training-deeper-neural-machine-translation","slug":"training-deeper-neural-machine-translation","title":"Training Deeper Neural Machine Translation Models with Transparent Attention","date":"2018-08-22","arxiv_id":"1808.07561","n_code_links":1,"syntology":null},{"paper":null,"slug":"learning-to-exploit-invariances-in-clinical","title":"Learning to Exploit Invariances in Clinical Time-Series Data using Sequence Transformer Networks","date":"2018-08-21","arxiv_id":"1808.06725","n_code_links":0,"syntology":null},{"paper":null,"slug":"veram-view-enhanced-recurrent-attention-model","title":"VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification","date":"2018-08-20","arxiv_id":"1808.06698","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-quantize-deep-networks-by","title":"Learning to Quantize Deep Networks by Optimizing Quantization Intervals with Task Loss","date":"2018-08-17","arxiv_id":"1808.05779","n_code_links":0,"syntology":null},{"paper":"/paper/larnn-linear-attention-recurrent-neural","slug":"larnn-linear-attention-recurrent-neural","title":"LARNN: Linear Attention Recurrent Neural Network","date":"2018-08-16","arxiv_id":"1808.05578","n_code_links":1,"syntology":null},{"paper":"/paper/metric-learning-for-novelty-and-anomaly","slug":"metric-learning-for-novelty-and-anomaly","title":"Metric Learning for Novelty and Anomaly Detection","date":"2018-08-16","arxiv_id":"1808.05492","n_code_links":1,"syntology":null},{"paper":"/paper/dnn-feature-map-compression-using-learned","slug":"dnn-feature-map-compression-using-learned","title":"DNN Feature Map Compression using Learned Representation over GF(2)","date":"2018-08-15","arxiv_id":"1808.05285","n_code_links":1,"syntology":null},{"paper":null,"slug":"cache-telepathy-leveraging-shared-resource","title":"Cache Telepathy: Leveraging Shared Resource Attacks to Learn DNN Architectures","date":"2018-08-14","arxiv_id":"1808.04761","n_code_links":0,"syntology":null},{"paper":"/paper/improving-generalization-via-scalable","slug":"improving-generalization-via-scalable","title":"Improving Generalization via Scalable Neighborhood Component Analysis","date":"2018-08-14","arxiv_id":"1808.04699","n_code_links":2,"syntology":null},{"paper":null,"slug":"denseran-for-offline-handwritten-chinese","title":"DenseRAN for Offline Handwritten Chinese Character Recognition","date":"2018-08-13","arxiv_id":"1808.04134","n_code_links":0,"syntology":null},{"paper":null,"slug":"fully-automated-analysis-of-body-composition","title":"Fully-Automated Analysis of Body Composition from CT in Cancer Patients Using Convolutional Neural Networks","date":"2018-08-11","arxiv_id":"1808.03844","n_code_links":0,"syntology":null},{"paper":null,"slug":"densely-connected-convolutional-networks-for","title":"Densely Connected Convolutional Networks for Speech Recognition","date":"2018-08-10","arxiv_id":"1808.03570","n_code_links":0,"syntology":null},{"paper":null,"slug":"relational-dynamic-memory-networks","title":"Relational dynamic memory networks","date":"2018-08-10","arxiv_id":"1808.04247","n_code_links":0,"syntology":null},{"paper":"/paper/character-level-language-modeling-with-deeper","slug":"character-level-language-modeling-with-deeper","title":"Character-Level Language Modeling with Deeper Self-Attention","date":"2018-08-09","arxiv_id":"1808.04444","n_code_links":1,"syntology":null},{"paper":"/paper/design-challenges-in-named-entity","slug":"design-challenges-in-named-entity","title":"Design Challenges in Named Entity Transliteration","date":"2018-08-07","arxiv_id":"1808.02563","n_code_links":1,"syntology":null},{"paper":null,"slug":"rethinking-numerical-representations-for-deep","title":"Rethinking Numerical Representations for Deep Neural Networks","date":"2018-08-07","arxiv_id":"1808.02513","n_code_links":0,"syntology":null},{"paper":null,"slug":"faceoff-anonymizing-videos-in-the-operating","title":"FaceOff: Anonymizing Videos in the Operating Rooms","date":"2018-08-06","arxiv_id":"1808.04440","n_code_links":0,"syntology":null},{"paper":null,"slug":"x-gans-image-reconstruction-made-easy-for","title":"X-GANs: Image Reconstruction Made Easy for Extreme Cases","date":"2018-08-06","arxiv_id":"1808.04432","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-multi-task-framework-for-skin-lesion","title":"A Multi-task Framework for Skin Lesion Detection and Segmentation","date":"2018-08-05","arxiv_id":"1808.01676","n_code_links":0,"syntology":null},{"paper":"/paper/is-robustness-the-cost-of-accuracy-a","slug":"is-robustness-the-cost-of-accuracy-a","title":"Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Models","date":"2018-08-05","arxiv_id":"1808.01688","n_code_links":2,"syntology":{"ran":0,"of":2,"n_ran_checked":0,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"0 ran · 2 unverified","official":{"repos":["huanzhang12/Adversarial_Survey"],"state":"official: not harvested","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":[]}}},{"paper":"/paper/skin-lesion-diagnosis-using-ensembles","slug":"skin-lesion-diagnosis-using-ensembles","title":"Skin Lesion Diagnosis using Ensembles, Unscaled Multi-Crop Evaluation and Loss Weighting","date":"2018-08-05","arxiv_id":"1808.01694","n_code_links":2,"syntology":null},{"paper":null,"slug":"on-lipschitz-bounds-of-general-convolutional","title":"On Lipschitz Bounds of General Convolutional Neural Networks","date":"2018-08-04","arxiv_id":"1808.01415","n_code_links":0,"syntology":null},{"paper":null,"slug":"teacher-guided-architecture-search","title":"Teacher Guided Architecture Search","date":"2018-08-04","arxiv_id":"1808.01405","n_code_links":0,"syntology":null},{"paper":null,"slug":"neural-machine-translation-with-decoding","title":"Neural Machine Translation with Decoding History Enhanced Attention","date":"2018-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/reinforced-evolutionary-neural-architecture","slug":"reinforced-evolutionary-neural-architecture","title":"Reinforced Evolutionary Neural Architecture Search","date":"2018-08-01","arxiv_id":"1808.00193","n_code_links":1,"syntology":null},{"paper":"/paper/slimnets-an-exploration-of-deep-model","slug":"slimnets-an-exploration-of-deep-model","title":"SlimNets: An Exploration of Deep Model Compression and Acceleration","date":"2018-08-01","arxiv_id":"1808.00496","n_code_links":1,"syntology":null},{"paper":null,"slug":"trapacc-and-trapaccs-at-parseme-shared-task","title":"TRAPACC and TRAPACCS at PARSEME Shared Task 2018: Neural Transition Tagging of Verbal Multiword Expressions","date":"2018-08-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/cutting-down-training-memory-by-re-fowarding","slug":"cutting-down-training-memory-by-re-fowarding","title":"Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs","date":"2018-07-31","arxiv_id":"1808.00079","n_code_links":1,"syntology":null},{"paper":"/paper/mnasnet-platform-aware-neural-architecture","slug":"mnasnet-platform-aware-neural-architecture","title":"MnasNet: Platform-Aware Neural Architecture Search for Mobile","date":"2018-07-31","arxiv_id":"1807.11626","n_code_links":29,"syntology":{"ran":4,"of":6,"n_ran_checked":3,"n_instrument":1,"unverified":2,"pointer_only":2,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["tensorflow/tpu"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":"/paper/segstereo-exploiting-semantic-information-for","slug":"segstereo-exploiting-semantic-information-for","title":"SegStereo: Exploiting Semantic Information for Disparity Estimation","date":"2018-07-31","arxiv_id":"1807.11699","n_code_links":0,"syntology":null},{"paper":"/paper/acquisition-of-localization-confidence-for","slug":"acquisition-of-localization-confidence-for","title":"Acquisition of Localization Confidence for Accurate Object Detection","date":"2018-07-30","arxiv_id":"1807.11590","n_code_links":4,"syntology":{"ran":17,"of":18,"n_ran_checked":15,"n_instrument":2,"unverified":1,"pointer_only":2,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 0 honoured, 0 violated, 15 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["vacancy/PreciseRoIPooling"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"doubly-attentive-transformer-machine","title":"Doubly Attentive Transformer Machine Translation","date":"2018-07-30","arxiv_id":"1807.11605","n_code_links":0,"syntology":null},{"paper":null,"slug":"extreme-network-compression-via-filter-group","title":"Extreme Network Compression via Filter Group Approximation","date":"2018-07-30","arxiv_id":"1807.11254","n_code_links":0,"syntology":null},{"paper":null,"slug":"highly-scalable-deep-learning-training-system","title":"Highly Scalable Deep Learning Training System with Mixed-Precision: Training ImageNet in Four Minutes","date":"2018-07-30","arxiv_id":"1807.11205","n_code_links":0,"syntology":null},{"paper":"/paper/shufflenet-v2-practical-guidelines-for","slug":"shufflenet-v2-practical-guidelines-for","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","date":"2018-07-30","arxiv_id":"1807.11164","n_code_links":35,"syntology":{"ran":14,"of":30,"n_ran_checked":13,"n_instrument":1,"unverified":16,"pointer_only":3,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 16 unverified","official":null}},{"paper":"/paper/adam-admm-a-unified-systematic-framework-of","slug":"adam-admm-a-unified-systematic-framework-of","title":"StructADMM: A Systematic, High-Efficiency Framework of Structured Weight Pruning for DNNs","date":"2018-07-29","arxiv_id":"1807.11091","n_code_links":1,"syntology":null},{"paper":"/paper/reenactgan-learning-to-reenact-faces-via","slug":"reenactgan-learning-to-reenact-faces-via","title":"ReenactGAN: Learning to Reenact Faces via Boundary Transfer","date":"2018-07-29","arxiv_id":"1807.11079","n_code_links":1,"syntology":null},{"paper":null,"slug":"characters-detection-on-namecard-with-faster","title":"Characters Detection on Namecard with faster RCNN","date":"2018-07-27","arxiv_id":"1807.10417","n_code_links":0,"syntology":null},{"paper":"/paper/a-better-baseline-for-ava","slug":"a-better-baseline-for-ava","title":"A Better Baseline for AVA","date":"2018-07-26","arxiv_id":"1807.10066","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-unified-approximation-framework-for-deep","title":"A Unified Approximation Framework for Compressing and Accelerating Deep Neural Networks","date":"2018-07-26","arxiv_id":"1807.10119","n_code_links":0,"syntology":null},{"paper":"/paper/lq-nets-learned-quantization-for-highly","slug":"lq-nets-learned-quantization-for-highly","title":"LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks","date":"2018-07-26","arxiv_id":"1807.10029","n_code_links":1,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Microsoft/LQ-Nets"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"coreset-based-neural-network-compression","title":"Coreset-Based Neural Network Compression","date":"2018-07-25","arxiv_id":"1807.09810","n_code_links":0,"syntology":null},{"paper":null,"slug":"crossbar-aware-neural-network-pruning","title":"Crossbar-aware neural network pruning","date":"2018-07-25","arxiv_id":"1807.10816","n_code_links":0,"syntology":null},{"paper":"/paper/two-at-once-enhancing-learning-and","slug":"two-at-once-enhancing-learning-and","title":"Two at Once: Enhancing Learning and Generalization Capacities via IBN-Net","date":"2018-07-25","arxiv_id":"1807.09441","n_code_links":25,"syntology":{"ran":8,"of":16,"n_ran_checked":7,"n_instrument":1,"unverified":8,"pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified","official":{"repos":["XingangPan/IBN-Net"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"paper":null,"slug":"unbounded-output-networks-for-classification","title":"Unbounded Output Networks for Classification","date":"2018-07-25","arxiv_id":"1807.09443","n_code_links":0,"syntology":null},{"paper":"/paper/git-loss-for-deep-face-recognition","slug":"git-loss-for-deep-face-recognition","title":"Git Loss for Deep Face Recognition","date":"2018-07-23","arxiv_id":"1807.08512","n_code_links":1,"syntology":null},{"paper":null,"slug":"text-classification-based-on-multiple-block","title":"Text Classification based on Multiple Block Convolutional Highways","date":"2018-07-23","arxiv_id":"1807.09602","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimal-continuous-state-pomdp-planning-with","title":"Optimal Continuous State POMDP Planning with Semantic Observations: A Variational Approach","date":"2018-07-22","arxiv_id":"1807.08229","n_code_links":0,"syntology":null},{"paper":null,"slug":"optimize-deep-convolutional-neural-network","title":"Optimize Deep Convolutional Neural Network with Ternarized Weights and High Accuracy","date":"2018-07-20","arxiv_id":"1807.07948","n_code_links":0,"syntology":null}],"record_sha256":"430160a34ad4ae072613230928ad4089f17cfd8c18dbcf00c3ed150d04a8748d","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}