{"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/relu/papers/103","list_of":"/method/relu","method":"ReLU","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":103,"pages_in_order":104,"rows_per_page":100,"rows":[10201,10300],"of":10350,"counts":{"archive_papers_tagged":10350,"with_a_code_link":4256,"where_syntology_ran_a_sample":1079,"not_listed_spam_title":0,"listed":10350,"listed_where_code_ran":1079,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":909,"every_run_a_failure_of_syntologys_instrument":170,"listed_with_a_run_with_no_instrument_failure":909,"listed_every_run_a_failure_of_syntologys_instrument":170,"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/relu","prev":"/method/relu/papers/102","next":"/method/relu/papers/104","papers":[{"paper":"/paper/human-pose-estimation-via-convolutional-part","slug":"human-pose-estimation-via-convolutional-part","title":"Human pose estimation via Convolutional Part Heatmap Regression","date":"2016-09-06","arxiv_id":"1609.01743","n_code_links":1,"syntology":null},{"paper":"/paper/pvanet-deep-but-lightweight-neural-networks","slug":"pvanet-deep-but-lightweight-neural-networks","title":"PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection","date":"2016-08-29","arxiv_id":"1608.08021","n_code_links":2,"syntology":null},{"paper":"/paper/densely-connected-convolutional-networks","slug":"densely-connected-convolutional-networks","title":"Densely Connected Convolutional Networks","date":"2016-08-25","arxiv_id":"1608.06993","n_code_links":146,"syntology":{"ran":48,"of":71,"n_ran_checked":32,"n_instrument":16,"unverified":23,"pointer_only":8,"phrase":"48 ran (of which 0 constructed an object rather than computing a result; 32 with no instrument failure: 1 honoured, 0 violated, 31 with no contract checked; 16 where Syntology's instrument failed) · 23 unverified","official":{"repos":["liuzhuang13/DenseNet"],"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/lets-keep-it-simple-using-simple","slug":"lets-keep-it-simple-using-simple","title":"Lets keep it simple, Using simple architectures to outperform deeper and more complex architectures","date":"2016-08-22","arxiv_id":"1608.06037","n_code_links":9,"syntology":{"ran":11,"of":11,"n_ran_checked":8,"n_instrument":3,"unverified":0,"pointer_only":0,"phrase":"11 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; 3 where Syntology's instrument failed) · 0 unverified","official":{"repos":["Coderx7/SimpleNet"],"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":"how-image-degradations-affect-deep-cnn-based","title":"How Image Degradations Affect Deep CNN-based Face Recognition?","date":"2016-08-18","arxiv_id":"1608.05246","n_code_links":0,"syntology":null},{"paper":"/paper/dynamic-network-surgery-for-efficient-dnns","slug":"dynamic-network-surgery-for-efficient-dnns","title":"Dynamic Network Surgery for Efficient DNNs","date":"2016-08-16","arxiv_id":"1608.04493","n_code_links":3,"syntology":null},{"paper":"/paper/design-of-efficient-convolutional-layers","slug":"design-of-efficient-convolutional-layers","title":"Design of Efficient Convolutional Layers using Single Intra-channel Convolution, Topological Subdivisioning and Spatial \"Bottleneck\" Structure","date":"2016-08-15","arxiv_id":"1608.04337","n_code_links":1,"syntology":null},{"paper":"/paper/learning-structured-sparsity-in-deep-neural","slug":"learning-structured-sparsity-in-deep-neural","title":"Learning Structured Sparsity in Deep Neural Networks","date":"2016-08-12","arxiv_id":"1608.03665","n_code_links":3,"syntology":{"ran":3,"of":14,"n_ran_checked":3,"n_instrument":0,"unverified":11,"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) · 11 unverified","official":{"repos":["wenwei202/caffe"],"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":"deep-vs-shallow-networks-an-approximation","title":"Deep vs. shallow networks : An approximation theory perspective","date":"2016-08-10","arxiv_id":"1608.03287","n_code_links":0,"syntology":null},{"paper":"/paper/faster-cnns-with-direct-sparse-convolutions","slug":"faster-cnns-with-direct-sparse-convolutions","title":"Faster CNNs with Direct Sparse Convolutions and Guided Pruning","date":"2016-08-04","arxiv_id":"1608.01409","n_code_links":1,"syntology":null},{"paper":"/paper/cuhk-ethz-siat-submission-to-activitynet","slug":"cuhk-ethz-siat-submission-to-activitynet","title":"CUHK & ETHZ & SIAT Submission to ActivityNet Challenge 2016","date":"2016-08-02","arxiv_id":"1608.00797","n_code_links":1,"syntology":null},{"paper":null,"slug":"25-years-of-cnns-can-we-compare-to-human","title":"25 years of CNNs: Can we compare to human abstraction capabilities?","date":"2016-07-28","arxiv_id":"1607.08366","n_code_links":0,"syntology":null},{"paper":null,"slug":"approximation-by-combinations-of-relu-and","title":"Approximation by Combinations of ReLU and Squared ReLU Ridge Functions with $ \\ell^1 $ and $ \\ell^0 $ Controls","date":"2016-07-26","arxiv_id":"1607.07819","n_code_links":0,"syntology":null},{"paper":null,"slug":"improved-deep-learning-of-object-category","title":"Improved Deep Learning of Object Category using Pose Information","date":"2016-07-20","arxiv_id":"1607.05836","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-recognize-objects-by-retaining","title":"Learning to Recognize Objects by Retaining other Factors of Variation","date":"2016-07-20","arxiv_id":"1607.05851","n_code_links":0,"syntology":null},{"paper":null,"slug":"collaborative-layer-wise-discriminative","title":"Collaborative Layer-wise Discriminative Learning in Deep Neural Networks","date":"2016-07-19","arxiv_id":"1607.05440","n_code_links":0,"syntology":null},{"paper":null,"slug":"bag-of-attributes-for-video-event-retrieval","title":"Bag of Attributes for Video Event Retrieval","date":"2016-07-18","arxiv_id":"1607.05208","n_code_links":0,"syntology":null},{"paper":"/paper/dsd-dense-sparse-dense-training-for-deep","slug":"dsd-dense-sparse-dense-training-for-deep","title":"DSD: Dense-Sparse-Dense Training for Deep Neural Networks","date":"2016-07-15","arxiv_id":"1607.04381","n_code_links":2,"syntology":null},{"paper":null,"slug":"intra-layer-nonuniform-quantization-for-deep","title":"Intra-layer Nonuniform Quantization for Deep Convolutional Neural Network","date":"2016-07-10","arxiv_id":"1607.02720","n_code_links":0,"syntology":null},{"paper":null,"slug":"nist-an-image-classification-network-to-image","title":"NIST: An Image Classification Network to Image Semantic Retrieval","date":"2016-07-02","arxiv_id":"1607.00464","n_code_links":0,"syntology":null},{"paper":"/paper/actor-critic-versus-direct-policy-search-a","slug":"actor-critic-versus-direct-policy-search-a","title":"Actor-critic versus direct policy search: a comparison based on sample complexity","date":"2016-06-29","arxiv_id":"1606.09152","n_code_links":1,"syntology":null},{"paper":"/paper/gaussian-error-linear-units-gelus","slug":"gaussian-error-linear-units-gelus","title":"Gaussian Error Linear Units (GELUs)","date":"2016-06-27","arxiv_id":"1606.08415","n_code_links":8,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"pointer_only":0,"phrase":"7 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","official":{"repos":["hendrycks/GELUs"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":2,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/3d-u-net-learning-dense-volumetric","slug":"3d-u-net-learning-dense-volumetric","title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","date":"2016-06-21","arxiv_id":"1606.06650","n_code_links":27,"syntology":{"ran":59,"of":76,"n_ran_checked":42,"n_instrument":17,"unverified":17,"pointer_only":20,"phrase":"59 ran (of which 18 constructed an object rather than computing a result; 42 with no instrument failure: 4 honoured, 0 violated, 38 with no contract checked; 17 where Syntology's instrument failed) · 17 unverified","official":null}},{"paper":"/paper/dorefa-net-training-low-bitwidth","slug":"dorefa-net-training-low-bitwidth","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","date":"2016-06-20","arxiv_id":"1606.06160","n_code_links":13,"syntology":{"ran":8,"of":13,"n_ran_checked":8,"n_instrument":0,"unverified":5,"pointer_only":1,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["tensorpack/tensorpack"],"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":"cltorch-a-hardware-agnostic-backend-for-the","title":"cltorch: a Hardware-Agnostic Backend for the Torch Deep Neural Network Library, Based on OpenCL","date":"2016-06-15","arxiv_id":"1606.04884","n_code_links":0,"syntology":null},{"paper":"/paper/infogan-interpretable-representation-learning","slug":"infogan-interpretable-representation-learning","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","date":"2016-06-12","arxiv_id":"1606.03657","n_code_links":38,"syntology":{"ran":5,"of":6,"n_ran_checked":1,"n_instrument":4,"unverified":1,"pointer_only":0,"phrase":"5 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; 4 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":"/paper/training-recurrent-answering-units-with-joint","slug":"training-recurrent-answering-units-with-joint","title":"Training Recurrent Answering Units with Joint Loss Minimization for VQA","date":"2016-06-12","arxiv_id":"1606.03647","n_code_links":0,"syntology":null},{"paper":"/paper/systematic-evaluation-of-cnn-advances-on-the","slug":"systematic-evaluation-of-cnn-advances-on-the","title":"Systematic evaluation of CNN advances on the ImageNet","date":"2016-06-07","arxiv_id":"1606.02228","n_code_links":1,"syntology":null},{"paper":"/paper/multimodal-compact-bilinear-pooling-for","slug":"multimodal-compact-bilinear-pooling-for","title":"Multimodal Compact Bilinear Pooling for Visual Question Answering and Visual Grounding","date":"2016-06-06","arxiv_id":"1606.01847","n_code_links":10,"syntology":null},{"paper":"/paper/deeplab-semantic-image-segmentation-with-deep","slug":"deeplab-semantic-image-segmentation-with-deep","title":"DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs","date":"2016-06-02","arxiv_id":"1606.00915","n_code_links":47,"syntology":{"ran":43,"of":63,"n_ran_checked":39,"n_instrument":4,"unverified":20,"pointer_only":18,"phrase":"43 ran (of which 12 constructed an object rather than computing a result; 39 with no instrument failure: 1 honoured, 0 violated, 38 with no contract checked; 4 where Syntology's instrument failed) · 20 unverified","official":null}},{"paper":"/paper/adversarial-feature-learning","slug":"adversarial-feature-learning","title":"Adversarial Feature Learning","date":"2016-05-31","arxiv_id":"1605.09782","n_code_links":10,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":"/paper/hierarchical-question-image-co-attention-for","slug":"hierarchical-question-image-co-attention-for","title":"Hierarchical Question-Image Co-Attention for Visual Question Answering","date":"2016-05-31","arxiv_id":"1606.00061","n_code_links":9,"syntology":{"ran":4,"of":7,"n_ran_checked":3,"n_instrument":1,"unverified":3,"pointer_only":1,"phrase":"4 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; 1 where Syntology's instrument failed) · 3 unverified","official":{"repos":["jiasenlu/HieCoAttenVQA"],"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":"going-deeper-for-multilingual-visual","title":"Going Deeper for Multilingual Visual Sentiment Detection","date":"2016-05-30","arxiv_id":"1605.09211","n_code_links":0,"syntology":null},{"paper":"/paper/parametric-exponential-linear-unit-for-deep","slug":"parametric-exponential-linear-unit-for-deep","title":"Parametric Exponential Linear Unit for Deep Convolutional Neural Networks","date":"2016-05-30","arxiv_id":"1605.09332","n_code_links":0,"syntology":null},{"paper":"/paper/density-estimation-using-real-nvp","slug":"density-estimation-using-real-nvp","title":"Density estimation using Real NVP","date":"2016-05-27","arxiv_id":"1605.08803","n_code_links":35,"syntology":{"ran":48,"of":70,"n_ran_checked":38,"n_instrument":10,"unverified":22,"pointer_only":33,"phrase":"48 ran (of which 26 constructed an object rather than computing a result; 38 with no instrument failure: 2 honoured, 0 violated, 36 with no contract checked; 10 where Syntology's instrument failed) · 22 unverified","official":null}},{"paper":"/paper/theano-mpi-a-theano-based-distributed","slug":"theano-mpi-a-theano-based-distributed","title":"Theano-MPI: a Theano-based Distributed Training Framework","date":"2016-05-26","arxiv_id":"1605.08325","n_code_links":1,"syntology":null},{"paper":null,"slug":"eventnet-version-11-technical-report","title":"EventNet Version 1.1 Technical Report","date":"2016-05-24","arxiv_id":"1605.07289","n_code_links":0,"syntology":null},{"paper":"/paper/fractalnet-ultra-deep-neural-networks-without","slug":"fractalnet-ultra-deep-neural-networks-without","title":"FractalNet: Ultra-Deep Neural Networks without Residuals","date":"2016-05-24","arxiv_id":"1605.07648","n_code_links":4,"syntology":{"ran":4,"of":6,"n_ran_checked":0,"n_instrument":4,"unverified":2,"pointer_only":1,"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) · 2 unverified","official":null}},{"paper":"/paper/self-paced-deep-learning-for-weakly","slug":"self-paced-deep-learning-for-weakly","title":"Self Paced Deep Learning for Weakly Supervised Object Detection","date":"2016-05-24","arxiv_id":"1605.07651","n_code_links":1,"syntology":null},{"paper":null,"slug":"path-normalized-optimization-of-recurrent","title":"Path-Normalized Optimization of Recurrent Neural Networks with ReLU Activations","date":"2016-05-23","arxiv_id":"1605.07154","n_code_links":0,"syntology":null},{"paper":"/paper/wide-residual-networks","slug":"wide-residual-networks","title":"Wide Residual Networks","date":"2016-05-23","arxiv_id":"1605.07146","n_code_links":72,"syntology":{"ran":66,"of":96,"n_ran_checked":48,"n_instrument":18,"unverified":30,"pointer_only":50,"phrase":"66 ran (of which 31 constructed an object rather than computing a result; 48 with no instrument failure: 0 honoured, 0 violated, 48 with no contract checked; 18 where Syntology's instrument failed) · 30 unverified","official":{"repos":["szagoruyko/wide-residual-networks"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"deep-roots-improving-cnn-efficiency-with","title":"Deep Roots: Improving CNN Efficiency with Hierarchical Filter Groups","date":"2016-05-20","arxiv_id":"1605.06489","n_code_links":0,"syntology":null},{"paper":"/paper/fully-convolutional-networks-for-semantic","slug":"fully-convolutional-networks-for-semantic","title":"Fully Convolutional Networks for Semantic Segmentation","date":"2016-05-20","arxiv_id":"1605.06211","n_code_links":37,"syntology":null},{"paper":"/paper/r-fcn-object-detection-via-region-based-fully","slug":"r-fcn-object-detection-via-region-based-fully","title":"R-FCN: Object Detection via Region-based Fully Convolutional Networks","date":"2016-05-20","arxiv_id":"1605.06409","n_code_links":48,"syntology":{"ran":7,"of":11,"n_ran_checked":6,"n_instrument":1,"unverified":4,"pointer_only":1,"phrase":"7 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; 1 where Syntology's instrument failed) · 4 unverified","official":{"repos":["daijifeng001/r-fcn"],"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/ristretto-hardware-oriented-approximation-of","slug":"ristretto-hardware-oriented-approximation-of","title":"Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks","date":"2016-05-20","arxiv_id":"1605.06402","n_code_links":2,"syntology":null},{"paper":null,"slug":"swapout-learning-an-ensemble-of-deep","title":"Swapout: Learning an ensemble of deep architectures","date":"2016-05-20","arxiv_id":"1605.06465","n_code_links":0,"syntology":null},{"paper":"/paper/deepercut-a-deeper-stronger-and-faster-multi","slug":"deepercut-a-deeper-stronger-and-faster-multi","title":"DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model","date":"2016-05-10","arxiv_id":"1605.03170","n_code_links":16,"syntology":null},{"paper":null,"slug":"adversarial-diversity-and-hard-positive","title":"Adversarial Diversity and Hard Positive Generation","date":"2016-05-05","arxiv_id":"1605.01775","n_code_links":0,"syntology":null},{"paper":null,"slug":"refining-architectures-of-deep-convolutional","title":"Refining Architectures of Deep Convolutional Neural Networks","date":"2016-04-22","arxiv_id":"1604.06832","n_code_links":0,"syntology":null},{"paper":"/paper/deep-saliency-with-encoded-low-level-distance","slug":"deep-saliency-with-encoded-low-level-distance","title":"Deep Saliency with Encoded Low level Distance Map and High Level Features","date":"2016-04-19","arxiv_id":"1604.05495","n_code_links":2,"syntology":null},{"paper":"/paper/deep-residual-networks-with-exponential","slug":"deep-residual-networks-with-exponential","title":"Deep Residual Networks with Exponential Linear Unit","date":"2016-04-14","arxiv_id":"1604.04112","n_code_links":1,"syntology":null},{"paper":"/paper/bridging-the-gaps-between-residual-learning","slug":"bridging-the-gaps-between-residual-learning","title":"Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex","date":"2016-04-13","arxiv_id":"1604.03640","n_code_links":4,"syntology":null},{"paper":"/paper/hardware-oriented-approximation-of","slug":"hardware-oriented-approximation-of","title":"Hardware-oriented Approximation of Convolutional Neural Networks","date":"2016-04-11","arxiv_id":"1604.03168","n_code_links":1,"syntology":null},{"paper":"/paper/t-cnn-tubelets-with-convolutional-neural","slug":"t-cnn-tubelets-with-convolutional-neural","title":"T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos","date":"2016-04-09","arxiv_id":"1604.02532","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":["myfavouritekk/T-CNN"],"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":"norm-preserving-orthogonal-permutation-linear","title":"Norm-preserving Orthogonal Permutation Linear Unit Activation Functions (OPLU)","date":"2016-04-08","arxiv_id":"1604.02313","n_code_links":0,"syntology":null},{"paper":"/paper/a-multipath-network-for-object-detection","slug":"a-multipath-network-for-object-detection","title":"A MultiPath Network for Object Detection","date":"2016-04-07","arxiv_id":"1604.02135","n_code_links":1,"syntology":null},{"paper":null,"slug":"multi-bias-non-linear-activation-in-deep","title":"Multi-Bias Non-linear Activation in Deep Neural Networks","date":"2016-04-03","arxiv_id":"1604.00676","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-learning-of-visual-1","slug":"unsupervised-learning-of-visual-1","title":"Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzles","date":"2016-03-30","arxiv_id":"1603.09246","n_code_links":9,"syntology":{"ran":10,"of":13,"n_ran_checked":7,"n_instrument":3,"unverified":3,"pointer_only":7,"phrase":"10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified","official":null}},{"paper":null,"slug":"instance-sensitive-fully-convolutional","title":"Instance-sensitive Fully Convolutional Networks","date":"2016-03-29","arxiv_id":"1603.08678","n_code_links":0,"syntology":null},{"paper":"/paper/learning-to-refine-object-segments","slug":"learning-to-refine-object-segments","title":"Learning to Refine Object Segments","date":"2016-03-29","arxiv_id":"1603.08695","n_code_links":2,"syntology":null},{"paper":"/paper/resnet-in-resnet-generalizing-residual","slug":"resnet-in-resnet-generalizing-residual","title":"Resnet in Resnet: Generalizing Residual Architectures","date":"2016-03-25","arxiv_id":"1603.08029","n_code_links":1,"syntology":null},{"paper":"/paper/stacked-hourglass-networks-for-human-pose","slug":"stacked-hourglass-networks-for-human-pose","title":"Stacked Hourglass Networks for Human Pose Estimation","date":"2016-03-22","arxiv_id":"1603.06937","n_code_links":46,"syntology":{"ran":24,"of":25,"n_ran_checked":22,"n_instrument":2,"unverified":1,"pointer_only":1,"phrase":"24 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 0 honoured, 0 violated, 22 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"accelerating-deep-neural-network-training","title":"Accelerating Deep Neural Network Training with Inconsistent Stochastic Gradient Descent","date":"2016-03-17","arxiv_id":"1603.05544","n_code_links":0,"syntology":null},{"paper":"/paper/identity-mappings-in-deep-residual-networks","slug":"identity-mappings-in-deep-residual-networks","title":"Identity Mappings in Deep Residual Networks","date":"2016-03-16","arxiv_id":"1603.05027","n_code_links":54,"syntology":{"ran":14,"of":25,"n_ran_checked":12,"n_instrument":2,"unverified":11,"pointer_only":2,"phrase":"14 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified","official":{"repos":["KaimingHe/resnet-1k-layers"],"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/understanding-and-improving-convolutional","slug":"understanding-and-improving-convolutional","title":"Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units","date":"2016-03-16","arxiv_id":"1603.05201","n_code_links":2,"syntology":null},{"paper":"/paper/xnor-net-imagenet-classification-using-binary","slug":"xnor-net-imagenet-classification-using-binary","title":"XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks","date":"2016-03-16","arxiv_id":"1603.05279","n_code_links":20,"syntology":{"ran":16,"of":18,"n_ran_checked":9,"n_instrument":7,"unverified":2,"pointer_only":3,"phrase":"16 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; 7 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":"/paper/hyperface-a-deep-multi-task-learning","slug":"hyperface-a-deep-multi-task-learning","title":"HyperFace: A Deep Multi-task Learning Framework for Face Detection, Landmark Localization, Pose Estimation, and Gender Recognition","date":"2016-03-03","arxiv_id":"1603.01249","n_code_links":2,"syntology":null},{"paper":"/paper/vdnn-virtualized-deep-neural-networks-for","slug":"vdnn-virtualized-deep-neural-networks-for","title":"vDNN: Virtualized Deep Neural Networks for Scalable, Memory-Efficient Neural Network Design","date":"2016-02-25","arxiv_id":"1602.08124","n_code_links":4,"syntology":null},{"paper":"/paper/squeezenet-alexnet-level-accuracy-with-50x","slug":"squeezenet-alexnet-level-accuracy-with-50x","title":"SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size","date":"2016-02-24","arxiv_id":"1602.07360","n_code_links":59,"syntology":{"ran":4,"of":4,"n_ran_checked":0,"n_instrument":4,"unverified":0,"pointer_only":2,"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) · 0 unverified","official":{"repos":["DT42/squeezenet_demo","DeepScale/SqueezeNet","Element-Research/dpnn","ejlb/squeezenet-chainer","haria/SqueezeNet"],"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/inception-v4-inception-resnet-and-the-impact","slug":"inception-v4-inception-resnet-and-the-impact","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","date":"2016-02-23","arxiv_id":"1602.07261","n_code_links":87,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":null}},{"paper":null,"slug":"revise-saturated-activation-functions","title":"Revise Saturated Activation Functions","date":"2016-02-18","arxiv_id":"1602.05980","n_code_links":0,"syntology":null},{"paper":null,"slug":"benefits-of-depth-in-neural-networks","title":"Benefits of depth in neural networks","date":"2016-02-14","arxiv_id":"1602.04485","n_code_links":0,"syntology":null},{"paper":"/paper/eie-efficient-inference-engine-on-compressed","slug":"eie-efficient-inference-engine-on-compressed","title":"EIE: Efficient Inference Engine on Compressed Deep Neural Network","date":"2016-02-04","arxiv_id":"1602.01528","n_code_links":4,"syntology":{"ran":2,"of":3,"n_ran_checked":2,"n_instrument":0,"unverified":1,"pointer_only":0,"phrase":"2 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; 0 where Syntology's instrument failed) · 1 unverified","official":null}},{"paper":null,"slug":"hybrid-cnn-and-dictionary-based-models-for","title":"Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation","date":"2016-01-29","arxiv_id":"1601.07977","n_code_links":0,"syntology":null},{"paper":null,"slug":"factors-in-finetuning-deep-model-for-object","title":"Factors in Finetuning Deep Model for object detection","date":"2016-01-20","arxiv_id":"1601.05150","n_code_links":0,"syntology":null},{"paper":"/paper/deep-learning-with-s-shaped-rectified-linear","slug":"deep-learning-with-s-shaped-rectified-linear","title":"Deep Learning with S-shaped Rectified Linear Activation Units","date":"2015-12-22","arxiv_id":"1512.07030","n_code_links":1,"syntology":null},{"paper":null,"slug":"poseidon-a-system-architecture-for-efficient","title":"Poseidon: A System Architecture for Efficient GPU-based Deep Learning on Multiple Machines","date":"2015-12-19","arxiv_id":"1512.06216","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-games-and-rademacher-observations","title":"Learning Games and Rademacher Observations Losses","date":"2015-12-16","arxiv_id":"1512.05244","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-deep-representation-learning-from-noisy","title":"On Deep Representation Learning from Noisy Web Images","date":"2015-12-15","arxiv_id":"1512.04785","n_code_links":0,"syntology":null},{"paper":"/paper/deep-residual-learning-for-image-recognition","slug":"deep-residual-learning-for-image-recognition","title":"Deep Residual Learning for Image Recognition","date":"2015-12-10","arxiv_id":"1512.03385","n_code_links":484,"syntology":{"ran":254,"of":377,"n_ran_checked":166,"n_instrument":88,"unverified":123,"pointer_only":193,"phrase":"254 ran (of which 108 constructed an object rather than computing a result; 166 with no instrument failure: 3 honoured, 1 violated, 162 with no contract checked; 88 where Syntology's instrument failed) · 123 unverified","official":{"repos":["KaimingHe/resnet-1k-layers"],"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/ssd-single-shot-multibox-detector","slug":"ssd-single-shot-multibox-detector","title":"SSD: Single Shot MultiBox Detector","date":"2015-12-08","arxiv_id":"1512.02325","n_code_links":221,"syntology":{"ran":93,"of":131,"n_ran_checked":79,"n_instrument":14,"unverified":38,"pointer_only":9,"phrase":"93 ran (of which 0 constructed an object rather than computing a result; 79 with no instrument failure: 3 honoured, 1 violated, 75 with no contract checked; 14 where Syntology's instrument failed) · 38 unverified","official":{"repos":["weiliu89/caffe"],"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":"deep-neural-decision-forests","title":"Deep Neural Decision Forests","date":"2015-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-both-weights-and-connections-for-1","title":"Learning both Weights and Connections for Efficient Neural Network","date":"2015-12-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/fast-and-accurate-deep-network-learning-by","slug":"fast-and-accurate-deep-network-learning-by","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","date":"2015-11-23","arxiv_id":"1511.07289","n_code_links":16,"syntology":{"ran":5,"of":7,"n_ran_checked":3,"n_instrument":2,"unverified":2,"pointer_only":2,"phrase":"5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"gradual-dropin-of-layers-to-train-very-deep","title":"Gradual DropIn of Layers to Train Very Deep Neural Networks","date":"2015-11-22","arxiv_id":"1511.06951","n_code_links":0,"syntology":null},{"paper":"/paper/compression-of-deep-convolutional-neural","slug":"compression-of-deep-convolutional-neural","title":"Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications","date":"2015-11-20","arxiv_id":"1511.06530","n_code_links":7,"syntology":{"ran":2,"of":9,"n_ran_checked":1,"n_instrument":1,"unverified":7,"pointer_only":9,"phrase":"2 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; 1 where Syntology's instrument failed) · 7 unverified","official":null}},{"paper":"/paper/all-you-need-is-a-good-init","slug":"all-you-need-is-a-good-init","title":"All you need is a good init","date":"2015-11-19","arxiv_id":"1511.06422","n_code_links":11,"syntology":{"ran":10,"of":19,"n_ran_checked":10,"n_instrument":0,"unverified":9,"pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified","official":{"repos":["ducha-aiki/LSUVinit"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"paper":"/paper/convolutional-neural-networks-with-low-rank","slug":"convolutional-neural-networks-with-low-rank","title":"Convolutional neural networks with low-rank regularization","date":"2015-11-19","arxiv_id":"1511.06067","n_code_links":2,"syntology":{"ran":1,"of":1,"n_ran_checked":0,"n_instrument":1,"unverified":0,"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","official":{"repos":["chengtaipu/lowrankcnn"],"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"]}}},{"paper":"/paper/deep-metric-learning-via-lifted-structured","slug":"deep-metric-learning-via-lifted-structured","title":"Deep Metric Learning via Lifted Structured Feature Embedding","date":"2015-11-19","arxiv_id":"1511.06452","n_code_links":3,"syntology":null},{"paper":"/paper/delving-deeper-into-convolutional-networks","slug":"delving-deeper-into-convolutional-networks","title":"Delving Deeper into Convolutional Networks for Learning Video Representations","date":"2015-11-19","arxiv_id":"1511.06432","n_code_links":6,"syntology":null},{"paper":null,"slug":"robust-convolutional-neural-networks-under","title":"Robust Convolutional Neural Networks under Adversarial Noise","date":"2015-11-19","arxiv_id":"1511.06306","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-representation-learning-with-1","slug":"unsupervised-representation-learning-with-1","title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","date":"2015-11-19","arxiv_id":"1511.06434","n_code_links":258,"syntology":{"ran":128,"of":219,"n_ran_checked":111,"n_instrument":17,"unverified":91,"pointer_only":111,"phrase":"128 ran (of which 61 constructed an object rather than computing a result; 111 with no instrument failure: 3 honoured, 0 violated, 108 with no contract checked; 17 where Syntology's instrument failed) · 91 unverified","official":null}},{"paper":"/paper/acdc-a-structured-efficient-linear-layer","slug":"acdc-a-structured-efficient-linear-layer","title":"ACDC: A Structured Efficient Linear Layer","date":"2015-11-18","arxiv_id":"1511.05946","n_code_links":2,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["mdenil/acdc-torch"],"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":"expressiveness-of-rectifier-networks","title":"Expressiveness of Rectifier Networks","date":"2015-11-18","arxiv_id":"1511.05678","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-are-deep-nets-reversible-a-simple-theory","title":"Why are deep nets reversible: A simple theory, with implications for training","date":"2015-11-18","arxiv_id":"1511.05653","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-neural-network-architectures-using","title":"Learning Neural Network Architectures using Backpropagation","date":"2015-11-17","arxiv_id":"1511.05497","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-to-assign-orientations-to-feature","title":"Learning to Assign Orientations to Feature Points","date":"2015-11-13","arxiv_id":"1511.04273","n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-quality-of-the-initial-basin-in","title":"On the Quality of the Initial Basin in Overspecified Neural Networks","date":"2015-11-13","arxiv_id":"1511.04210","n_code_links":0,"syntology":null},{"paper":null,"slug":"basic-level-categorization-facilitates-visual","title":"Basic Level Categorization Facilitates Visual Object Recognition","date":"2015-11-12","arxiv_id":"1511.04103","n_code_links":0,"syntology":null},{"paper":"/paper/bayesian-segnet-model-uncertainty-in-deep","slug":"bayesian-segnet-model-uncertainty-in-deep","title":"Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understanding","date":"2015-11-09","arxiv_id":"1511.02680","n_code_links":21,"syntology":{"ran":6,"of":18,"n_ran_checked":6,"n_instrument":0,"unverified":12,"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) · 12 unverified","official":null}}],"record_sha256":"93617e2775d1c7a415bfc348f3fe0fc41974f88f47bde08eb5c8baef1d673538","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}