{"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/368","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":368,"pages_in_order":375,"rows_per_page":100,"rows":[36701,36800],"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/367","next":"/method/softmax/papers/369","papers":[{"paper":null,"slug":"mpdcompress-matrix-permutation-decomposition","title":"MPDCompress - Matrix Permutation Decomposition Algorithm for Deep Neural Network Compression","date":"2018-05-30","arxiv_id":"1805.12085","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-function-convolutional-neural-networks","title":"Multi-function Convolutional Neural Networks for Improving Image Classification Performance","date":"2018-05-30","arxiv_id":"1805.11788","n_code_links":0,"syntology":null},{"paper":"/paper/superpixel-enhanced-pairwise-conditional","slug":"superpixel-enhanced-pairwise-conditional","title":"Superpixel-enhanced Pairwise Conditional Random Field for Semantic Segmentation","date":"2018-05-29","arxiv_id":"1805.11737","n_code_links":1,"syntology":null},{"paper":"/paper/deep-anomaly-detection-using-geometric","slug":"deep-anomaly-detection-using-geometric","title":"Deep Anomaly Detection Using Geometric Transformations","date":"2018-05-28","arxiv_id":"1805.10917","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":3,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["izikgo/AnomalyDetectionTransformations"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":"/paper/genattack-practical-black-box-attacks-with","slug":"genattack-practical-black-box-attacks-with","title":"GenAttack: Practical Black-box Attacks with Gradient-Free Optimization","date":"2018-05-28","arxiv_id":"1805.11090","n_code_links":3,"syntology":{"ran":5,"of":12,"n_ran_checked":5,"n_instrument":0,"unverified":7,"pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","official":{"repos":["nesl/adversarial_genattack"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"paper":"/paper/improving-the-resolution-of-cnn-feature-maps","slug":"improving-the-resolution-of-cnn-feature-maps","title":"Improving the Resolution of CNN Feature Maps Efficiently with Multisampling","date":"2018-05-28","arxiv_id":"1805.10766","n_code_links":2,"syntology":null},{"paper":"/paper/sacrificing-accuracy-for-reduced-computation","slug":"sacrificing-accuracy-for-reduced-computation","title":"Dynamically Sacrificing Accuracy for Reduced Computation: Cascaded Inference Based on Softmax Confidence","date":"2018-05-28","arxiv_id":"1805.10982","n_code_links":1,"syntology":null},{"paper":null,"slug":"sigsoftmax-reanalysis-of-the-softmax","title":"Sigsoftmax: Reanalysis of the Softmax Bottleneck","date":"2018-05-28","arxiv_id":"1805.10829","n_code_links":0,"syntology":null},{"paper":"/paper/theory-and-experiments-on-vector-quantized","slug":"theory-and-experiments-on-vector-quantized","title":"Theory and Experiments on Vector Quantized Autoencoders","date":"2018-05-28","arxiv_id":"1805.11063","n_code_links":2,"syntology":null},{"paper":null,"slug":"compact-and-computationally-efficient","title":"Compact and Computationally Efficient Representation of Deep Neural Networks","date":"2018-05-27","arxiv_id":"1805.10692","n_code_links":0,"syntology":null},{"paper":null,"slug":"heterogeneous-bitwidth-binarization-in","title":"Heterogeneous Bitwidth Binarization in Convolutional Neural Networks","date":"2018-05-25","arxiv_id":"1805.10368","n_code_links":0,"syntology":null},{"paper":null,"slug":"japanese-predicate-conjugation-for-neural","title":"Japanese Predicate Conjugation for Neural Machine Translation","date":"2018-05-25","arxiv_id":"1805.10047","n_code_links":0,"syntology":null},{"paper":null,"slug":"three-dimensional-radiotherapy-dose","title":"Three-Dimensional Radiotherapy Dose Prediction on Head and Neck Cancer Patients with a Hierarchically Densely Connected U-net Deep Learning Architecture","date":"2018-05-25","arxiv_id":"1805.10397","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-neural-machine-translation","title":"Fast Neural Machine Translation Implementation","date":"2018-05-24","arxiv_id":"1805.09863","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-scale-densenet-based-electricity-theft","title":"Multi-Scale DenseNet-Based Electricity Theft Detection","date":"2018-05-24","arxiv_id":"1805.09591","n_code_links":0,"syntology":null},{"paper":null,"slug":"building-extraction-at-scale-using","title":"Building Extraction at Scale using Convolutional Neural Network: Mapping of the United States","date":"2018-05-23","arxiv_id":"1805.08946","n_code_links":0,"syntology":null},{"paper":null,"slug":"saliency-deep-embedding-for-aurora-image","title":"Saliency deep embedding for aurora image search","date":"2018-05-23","arxiv_id":"1805.09033","n_code_links":0,"syntology":null},{"paper":"/paper/sniper-efficient-multi-scale-training","slug":"sniper-efficient-multi-scale-training","title":"SNIPER: Efficient Multi-Scale Training","date":"2018-05-23","arxiv_id":"1805.09300","n_code_links":4,"syntology":null},{"paper":null,"slug":"cascadecnn-pushing-the-performance-limits-of","title":"CascadeCNN: Pushing the performance limits of quantisation","date":"2018-05-22","arxiv_id":"1805.08743","n_code_links":0,"syntology":null},{"paper":null,"slug":"classification-uncertainty-of-deep-neural","title":"Classification Uncertainty of Deep Neural Networks Based on Gradient Information","date":"2018-05-22","arxiv_id":"1805.08440","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-person-detection-on-omnidirectional","title":"Improved Person Detection on Omnidirectional Images with Non-maxima Suppression","date":"2018-05-22","arxiv_id":"1805.08503","n_code_links":0,"syntology":null},{"paper":null,"slug":"maximum-causal-tsallis-entropy-imitation","title":"Maximum Causal Tsallis Entropy Imitation Learning","date":"2018-05-22","arxiv_id":"1805.08336","n_code_links":0,"syntology":null},{"paper":null,"slug":"training-convolutional-networks-with-web","title":"Training Convolutional Networks with Web Images","date":"2018-05-22","arxiv_id":"1805.08416","n_code_links":0,"syntology":null},{"paper":null,"slug":"compression-of-deep-convolutional-neural-1","title":"Compression of Deep Convolutional Neural Networks under Joint Sparsity Constraints","date":"2018-05-21","arxiv_id":"1805.08303","n_code_links":0,"syntology":null},{"paper":"/paper/self-attention-generative-adversarial","slug":"self-attention-generative-adversarial","title":"Self-Attention Generative Adversarial Networks","date":"2018-05-21","arxiv_id":"1805.08318","n_code_links":48,"syntology":{"ran":46,"of":81,"n_ran_checked":42,"n_instrument":4,"unverified":35,"pointer_only":3,"phrase":"46 ran (of which 0 constructed an object rather than computing a result; 42 with no instrument failure: 2 honoured, 0 violated, 40 with no contract checked; 4 where Syntology's instrument failed) · 35 unverified","official":{"repos":["brain-research/self-attention-gan"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":7,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"cappronet-deep-feature-learning-via","title":"CapProNet: Deep Feature Learning via Orthogonal Projections onto Capsule Subspaces","date":"2018-05-19","arxiv_id":"1805.07621","n_code_links":0,"syntology":null},{"paper":null,"slug":"minimum-margin-loss-for-deep-face-recognition","title":"Minimum Margin Loss for Deep Face Recognition","date":"2018-05-17","arxiv_id":"1805.06741","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-comparison-of-modeling-units-in-sequence-to","title":"A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese","date":"2018-05-16","arxiv_id":"1805.06239","n_code_links":0,"syntology":null},{"paper":"/paper/object-detection-at-200-frames-per-second","slug":"object-detection-at-200-frames-per-second","title":"Object detection at 200 Frames Per Second","date":"2018-05-16","arxiv_id":"1805.06361","n_code_links":1,"syntology":null},{"paper":"/paper/learning-rich-features-for-image-manipulation","slug":"learning-rich-features-for-image-manipulation","title":"Learning Rich Features for Image Manipulation Detection","date":"2018-05-13","arxiv_id":"1805.04953","n_code_links":2,"syntology":{"ran":6,"of":8,"n_ran_checked":6,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"classification-of-protein-crystallization-x","title":"Classification of Protein Crystallization X-Ray Images Using Major Convolutional Neural Network Architectures","date":"2018-05-11","arxiv_id":"1805.04563","n_code_links":0,"syntology":null},{"paper":null,"slug":"ensemble-soft-margin-softmax-loss-for-image","title":"Ensemble Soft-Margin Softmax Loss for Image Classification","date":"2018-05-10","arxiv_id":"1805.03922","n_code_links":0,"syntology":null},{"paper":null,"slug":"laconic-deep-learning-computing","title":"Laconic Deep Learning Computing","date":"2018-05-10","arxiv_id":"1805.04513","n_code_links":0,"syntology":null},{"paper":null,"slug":"unifying-data-model-and-hybrid-parallelism-in","title":"Unifying Data, Model and Hybrid Parallelism in Deep Learning via Tensor Tiling","date":"2018-05-10","arxiv_id":"1805.04170","n_code_links":0,"syntology":null},{"paper":"/paper/robust-classification-with-convolutional","slug":"robust-classification-with-convolutional","title":"Robust Classification with Convolutional Prototype Learning","date":"2018-05-09","arxiv_id":"1805.03438","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":0,"n_instrument":3,"unverified":2,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["YangHM/Convolutional-Prototype-Learning"],"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":["listed","unlocated"]}}},{"paper":"/paper/online-normalizer-calculation-for-softmax","slug":"online-normalizer-calculation-for-softmax","title":"Online normalizer calculation for softmax","date":"2018-05-08","arxiv_id":"1805.02867","n_code_links":1,"syntology":null},{"paper":null,"slug":"the-effectiveness-of-instance-normalization-a","title":"The Effectiveness of Instance Normalization: a Strong Baseline for Single Image Dehazing","date":"2018-05-08","arxiv_id":"1805.03305","n_code_links":0,"syntology":null},{"paper":null,"slug":"quantization-mimic-towards-very-tiny-cnn-for","title":"Quantization Mimic: Towards Very Tiny CNN for Object Detection","date":"2018-05-06","arxiv_id":"1805.02152","n_code_links":0,"syntology":null},{"paper":null,"slug":"squeezejet-high-level-synthesis-accelerator","title":"SqueezeJet: High-level Synthesis Accelerator Design for Deep Convolutional Neural Networks","date":"2018-05-06","arxiv_id":"1805.08695","n_code_links":0,"syntology":null},{"paper":null,"slug":"rifcn-recurrent-network-in-fully","title":"RiFCN: Recurrent Network in Fully Convolutional Network for Semantic Segmentation of High Resolution Remote Sensing Images","date":"2018-05-05","arxiv_id":"1805.02091","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-feature-learning-via-non","slug":"unsupervised-feature-learning-via-non","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","date":"2018-05-05","arxiv_id":"1805.01978","n_code_links":15,"syntology":{"ran":19,"of":23,"n_ran_checked":17,"n_instrument":2,"unverified":4,"pointer_only":16,"phrase":"19 ran (of which 14 constructed an object rather than computing a result; 17 with no instrument failure: 0 honoured, 0 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified","official":{"repos":["zhirongw/lemniscate.pytorch"],"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/extreme-adaptation-for-personalized-neural","slug":"extreme-adaptation-for-personalized-neural","title":"Extreme Adaptation for Personalized Neural Machine Translation","date":"2018-05-04","arxiv_id":"1805.01817","n_code_links":1,"syntology":null},{"paper":null,"slug":"an-end-to-end-approach-for-handling-unknown","title":"An End-to-end Approach for Handling Unknown Slot Values in Dialogue State Tracking","date":"2018-05-03","arxiv_id":"1805.01555","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-data-driven-residential-transformer","title":"A Data-Driven Residential Transformer Overloading Risk Assessment Method","date":"2018-05-02","arxiv_id":"1805.00630","n_code_links":0,"syntology":null},{"paper":"/paper/accelerating-neural-transformer-via-an","slug":"accelerating-neural-transformer-via-an","title":"Accelerating Neural Transformer via an Average Attention Network","date":"2018-05-02","arxiv_id":"1805.00631","n_code_links":1,"syntology":{"ran":7,"of":19,"n_ran_checked":7,"n_instrument":0,"unverified":12,"pointer_only":0,"phrase":"7 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; 0 where Syntology's instrument failed) · 12 unverified","official":{"repos":["bzhangXMU/transformer-aan"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":12,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"deep-perm-set-net-learn-to-predict-sets-with","title":"Deep Perm-Set Net: Learn to predict sets with unknown permutation and cardinality using deep neural networks","date":"2018-05-02","arxiv_id":"1805.00613","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-taxonomy-for-neural-memory-networks","title":"A Taxonomy for Neural Memory Networks","date":"2018-05-01","arxiv_id":"1805.00327","n_code_links":0,"syntology":null},{"paper":null,"slug":"localization-a-missing-link-in-the-pipeline","title":"Localization: A Missing Link in the Pipeline of Object Matching and Registration","date":"2018-05-01","arxiv_id":"1805.00223","n_code_links":0,"syntology":null},{"paper":null,"slug":"an-anti-fraud-system-for-car-insurance-claim","title":"An Anti-fraud System for Car Insurance Claim Based on Visual Evidence","date":"2018-04-30","arxiv_id":"1804.11207","n_code_links":0,"syntology":null},{"paper":"/paper/machine-learning-for-exam-triage","slug":"machine-learning-for-exam-triage","title":"Machine Learning for Exam Triage","date":"2018-04-30","arxiv_id":"1805.00503","n_code_links":1,"syntology":null},{"paper":null,"slug":"ultra-power-efficient-cnn-domain-specific","title":"Ultra Power-Efficient CNN Domain Specific Accelerator with 9.3TOPS/Watt for Mobile and Embedded Applications","date":"2018-04-30","arxiv_id":"1805.00361","n_code_links":0,"syntology":null},{"paper":null,"slug":"craft-complementary-recommendations-using","title":"CRAFT: Complementary Recommendations Using Adversarial Feature Transformer","date":"2018-04-29","arxiv_id":"1804.10871","n_code_links":0,"syntology":null},{"paper":null,"slug":"scalable-angular-discriminative-deep-metric","title":"Scalable Angular Discriminative Deep Metric Learning for Face Recognition","date":"2018-04-29","arxiv_id":"1804.10899","n_code_links":0,"syntology":null},{"paper":null,"slug":"cram-clued-recurrent-attention-model","title":"CRAM: Clued Recurrent Attention Model","date":"2018-04-28","arxiv_id":"1804.10844","n_code_links":0,"syntology":null},{"paper":"/paper/syllable-based-sequence-to-sequence-speech","slug":"syllable-based-sequence-to-sequence-speech","title":"Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese","date":"2018-04-28","arxiv_id":"1804.10752","n_code_links":1,"syntology":null},{"paper":"/paper/visual-relationship-detection-with-deep","slug":"visual-relationship-detection-with-deep","title":"Visual relationship detection with deep structural ranking","date":"2018-04-27","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/accelerator-aware-pruning-for-convolutional","slug":"accelerator-aware-pruning-for-convolutional","title":"Accelerator-Aware Pruning for Convolutional Neural Networks","date":"2018-04-26","arxiv_id":"1804.09862","n_code_links":3,"syntology":null},{"paper":null,"slug":"on-deep-speaker-embeddings-for-text","title":"On deep speaker embeddings for text-independent speaker recognition","date":"2018-04-26","arxiv_id":"1804.10080","n_code_links":0,"syntology":null},{"paper":"/paper/the-best-of-both-worlds-combining-recent","slug":"the-best-of-both-worlds-combining-recent","title":"The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation","date":"2018-04-26","arxiv_id":"1804.09849","n_code_links":3,"syntology":null},{"paper":"/paper/applying-faster-r-cnn-for-object-detection-on","slug":"applying-faster-r-cnn-for-object-detection-on","title":"Applying Faster R-CNN for Object Detection on Malaria Images","date":"2018-04-25","arxiv_id":"1804.09548","n_code_links":2,"syntology":null},{"paper":null,"slug":"an-anchor-free-region-proposal-network-for","title":"An Anchor-Free Region Proposal Network for Faster R-CNN based Text Detection Approaches","date":"2018-04-24","arxiv_id":"1804.09003","n_code_links":0,"syntology":null},{"paper":"/paper/crawling-in-rogues-dungeons-with-partitioned","slug":"crawling-in-rogues-dungeons-with-partitioned","title":"Crawling in Rogue's dungeons with (partitioned) A3C","date":"2018-04-23","arxiv_id":"1804.08685","n_code_links":1,"syntology":null},{"paper":null,"slug":"deep-cross-domain-building-extraction-for","title":"Deep cross-domain building extraction for selective depth estimation from oblique aerial imagery","date":"2018-04-23","arxiv_id":"1804.08302","n_code_links":0,"syntology":null},{"paper":null,"slug":"inducing-and-embedding-senses-with-scaled","title":"Inducing and Embedding Senses with Scaled Gumbel Softmax","date":"2018-04-22","arxiv_id":"1804.08077","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-head-decoder-for-end-to-end-speech","title":"Multi-Head Decoder for End-to-End Speech Recognition","date":"2018-04-22","arxiv_id":"1804.08050","n_code_links":0,"syntology":null},{"paper":"/paper/adef-an-iterative-algorithm-to-construct","slug":"adef-an-iterative-algorithm-to-construct","title":"ADef: an Iterative Algorithm to Construct Adversarial Deformations","date":"2018-04-20","arxiv_id":"1804.07729","n_code_links":2,"syntology":{"ran":4,"of":4,"n_ran_checked":1,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"4 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; 3 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/automatic-stance-detection-using-end-to-end","slug":"automatic-stance-detection-using-end-to-end","title":"Automatic Stance Detection Using End-to-End Memory Networks","date":"2018-04-20","arxiv_id":"1804.07581","n_code_links":0,"syntology":null},{"paper":null,"slug":"generating-a-fusion-image-ones-identity-and","title":"Generating a Fusion Image: One's Identity and Another's Shape","date":"2018-04-20","arxiv_id":"1804.07455","n_code_links":0,"syntology":null},{"paper":"/paper/rethinking-the-faster-r-cnn-architecture-for","slug":"rethinking-the-faster-r-cnn-architecture-for","title":"Rethinking the Faster R-CNN Architecture for Temporal Action Localization","date":"2018-04-20","arxiv_id":"1804.07667","n_code_links":0,"syntology":null},{"paper":null,"slug":"value-aware-quantization-for-training-and","title":"Value-aware Quantization for Training and Inference of Neural Networks","date":"2018-04-20","arxiv_id":"1804.07802","n_code_links":0,"syntology":null},{"paper":null,"slug":"gnas-a-greedy-neural-architecture-search","title":"GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning","date":"2018-04-19","arxiv_id":"1804.06964","n_code_links":0,"syntology":null},{"paper":"/paper/detnet-a-backbone-network-for-object","slug":"detnet-a-backbone-network-for-object","title":"DetNet: A Backbone network for Object Detection","date":"2018-04-17","arxiv_id":"1804.06215","n_code_links":2,"syntology":null},{"paper":"/paper/igcv2-interleaved-structured-sparse","slug":"igcv2-interleaved-structured-sparse","title":"IGCV$2$: Interleaved Structured Sparse Convolutional Neural Networks","date":"2018-04-17","arxiv_id":"1804.06202","n_code_links":2,"syntology":null},{"paper":null,"slug":"deep-embedding-kernel","title":"Deep Embedding Kernel","date":"2018-04-16","arxiv_id":"1804.05806","n_code_links":0,"syntology":null},{"paper":"/paper/shapeshifter-robust-physical-adversarial","slug":"shapeshifter-robust-physical-adversarial","title":"ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector","date":"2018-04-16","arxiv_id":"1804.05810","n_code_links":3,"syntology":{"ran":3,"of":5,"n_ran_checked":2,"n_instrument":1,"unverified":2,"pointer_only":4,"phrase":"3 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; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["shangtse/robust-physical-attack"],"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":null,"slug":"sparsenet-a-sparse-densenet-for-image","title":"SparseNet: A Sparse DenseNet for Image Classification","date":"2018-04-15","arxiv_id":"1804.05340","n_code_links":0,"syntology":null},{"paper":"/paper/exploring-the-encoding-layer-and-loss","slug":"exploring-the-encoding-layer-and-loss","title":"Exploring the Encoding Layer and Loss Function in End-to-End Speaker and Language Recognition System","date":"2018-04-14","arxiv_id":"1804.05160","n_code_links":1,"syntology":null},{"paper":"/paper/-cudnn-accelerating-deep-learning-frameworks","slug":"-cudnn-accelerating-deep-learning-frameworks","title":"μ-cuDNN: Accelerating Deep Learning Frameworks with Micro-Batching","date":"2018-04-13","arxiv_id":"1804.04806","n_code_links":1,"syntology":null},{"paper":null,"slug":"transformation-on-computer-generated-facial","title":"Transformation on Computer-Generated Facial Image to Avoid Detection by Spoofing Detector","date":"2018-04-12","arxiv_id":"1804.04418","n_code_links":0,"syntology":null},{"paper":"/paper/adafactor-adaptive-learning-rates-with","slug":"adafactor-adaptive-learning-rates-with","title":"Adafactor: Adaptive Learning Rates with Sublinear Memory Cost","date":"2018-04-11","arxiv_id":"1804.04235","n_code_links":5,"syntology":{"ran":4,"of":4,"n_ran_checked":4,"n_instrument":0,"unverified":0,"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","official":null}},{"paper":"/paper/hybrid-binary-networks-optimizing-for","slug":"hybrid-binary-networks-optimizing-for","title":"Hybrid Binary Networks: Optimizing for Accuracy, Efficiency and Memory","date":"2018-04-11","arxiv_id":"1804.03867","n_code_links":1,"syntology":null},{"paper":"/paper/a-systematic-dnn-weight-pruning-framework","slug":"a-systematic-dnn-weight-pruning-framework","title":"A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers","date":"2018-04-10","arxiv_id":"1804.03294","n_code_links":4,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["KaiqiZhang/admm-pruning"],"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":"loss-rank-mining-a-general-hard-example","title":"Loss Rank Mining: A General Hard Example Mining Method for Real-time Detectors","date":"2018-04-10","arxiv_id":"1804.04606","n_code_links":0,"syntology":null},{"paper":null,"slug":"pilot-comparative-study-of-different-deep","title":"Pilot Comparative Study of Different Deep Features for Palmprint Identification in Low-Quality Images","date":"2018-04-10","arxiv_id":"1804.04602","n_code_links":0,"syntology":null},{"paper":"/paper/semi-supervised-adversarial-learning-to","slug":"semi-supervised-adversarial-learning-to","title":"Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model","date":"2018-04-10","arxiv_id":"1804.03675","n_code_links":1,"syntology":null},{"paper":"/paper/hyperdense-net-a-hyper-densely-connected-cnn","slug":"hyperdense-net-a-hyper-densely-connected-cnn","title":"HyperDense-Net: A hyper-densely connected CNN for multi-modal image segmentation","date":"2018-04-09","arxiv_id":"1804.02967","n_code_links":3,"syntology":{"ran":3,"of":3,"n_ran_checked":0,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["josedolz/HyperDenseNet"],"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/netadapt-platform-aware-neural-network","slug":"netadapt-platform-aware-neural-network","title":"NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications","date":"2018-04-09","arxiv_id":"1804.03230","n_code_links":4,"syntology":{"ran":1,"of":1,"n_ran_checked":1,"n_instrument":0,"unverified":0,"pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/recovering-realistic-texture-in-image-super","slug":"recovering-realistic-texture-in-image-super","title":"Recovering Realistic Texture in Image Super-resolution by Deep Spatial Feature Transform","date":"2018-04-09","arxiv_id":"1804.02815","n_code_links":4,"syntology":null},{"paper":"/paper/yolov3-an-incremental-improvement","slug":"yolov3-an-incremental-improvement","title":"YOLOv3: An Incremental Improvement","date":"2018-04-08","arxiv_id":"1804.02767","n_code_links":311,"syntology":{"ran":94,"of":124,"n_ran_checked":83,"n_instrument":11,"unverified":30,"pointer_only":24,"phrase":"94 ran (of which 0 constructed an object rather than computing a result; 83 with no instrument failure: 4 honoured, 2 violated, 77 with no contract checked; 11 where Syntology's instrument failed) · 30 unverified","official":null}},{"paper":null,"slug":"statistical-transformer-networks-learning","title":"Statistical transformer networks: learning shape and appearance models via self supervision","date":"2018-04-07","arxiv_id":"1804.02541","n_code_links":0,"syntology":null},{"paper":null,"slug":"question-type-guided-attention-in-visual","title":"Question Type Guided Attention in Visual Question Answering","date":"2018-04-06","arxiv_id":"1804.02088","n_code_links":0,"syntology":null},{"paper":null,"slug":"crystal-loss-and-quality-pooling-for","title":"Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition","date":"2018-04-03","arxiv_id":"1804.01159","n_code_links":0,"syntology":null},{"paper":"/paper/end-to-end-dense-video-captioning-with-masked","slug":"end-to-end-dense-video-captioning-with-masked","title":"End-to-End Dense Video Captioning with Masked Transformer","date":"2018-04-03","arxiv_id":"1804.00819","n_code_links":1,"syntology":null},{"paper":null,"slug":"a-vehicle-detection-approach-using-deep","title":"A Vehicle Detection Approach using Deep Learning Methodologies","date":"2018-04-02","arxiv_id":"1804.00429","n_code_links":0,"syntology":null},{"paper":null,"slug":"average-biased-relu-based-cnn-descriptor-for","title":"Average Biased ReLU Based CNN Descriptor for Improved Face Retrieval","date":"2018-04-02","arxiv_id":"1804.02051","n_code_links":0,"syntology":null},{"paper":null,"slug":"end-to-end-detection-and-re-identification","title":"End-to-End Detection and Re-identification Integrated Net for Person Search","date":"2018-04-02","arxiv_id":"1804.00376","n_code_links":0,"syntology":null},{"paper":"/paper/multi-scale-location-aware-kernel","slug":"multi-scale-location-aware-kernel","title":"Multi-scale Location-aware Kernel Representation for Object Detection","date":"2018-04-02","arxiv_id":"1804.00428","n_code_links":2,"syntology":null},{"paper":"/paper/training-tips-for-the-transformer-model","slug":"training-tips-for-the-transformer-model","title":"Training Tips for the Transformer Model","date":"2018-04-01","arxiv_id":"1804.00247","n_code_links":4,"syntology":null},{"paper":"/paper/human-semantic-parsing-for-person-re","slug":"human-semantic-parsing-for-person-re","title":"Human Semantic Parsing for Person Re-identification","date":"2018-03-31","arxiv_id":"1804.00216","n_code_links":0,"syntology":null},{"paper":null,"slug":"efficient-and-deep-person-re-identification","title":"Efficient and Deep Person Re-Identification using Multi-Level Similarity","date":"2018-03-30","arxiv_id":"1803.11353","n_code_links":0,"syntology":null}],"record_sha256":"254be566590b38324b4c60eb6d5f60b78e1278cb34b77abe56d100efe779385c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}