{"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/90","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":90,"pages_in_order":104,"rows_per_page":100,"rows":[8901,9000],"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/89","next":"/method/relu/papers/91","papers":[{"paper":null,"slug":"accumulation-bit-width-scaling-for-ultra-low","title":"Accumulation Bit-Width Scaling For Ultra-Low Precision Training Of Deep Networks","date":"2019-01-19","arxiv_id":"1901.06588","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-mutually-local-global-u-nets-for","title":"Learning Mutually Local-global U-nets For High-resolution Retinal Lesion Segmentation in Fundus Images","date":"2019-01-18","arxiv_id":"1901.06047","n_code_links":0,"syntology":null},{"paper":null,"slug":"machine-learning-with-clos-networks","title":"Machine Learning with Clos Networks","date":"2019-01-18","arxiv_id":"1901.06433","n_code_links":0,"syntology":null},{"paper":"/paper/on-policy-trust-region-policy-optimisation","slug":"on-policy-trust-region-policy-optimisation","title":"On-Policy Trust Region Policy Optimisation with Replay Buffers","date":"2019-01-18","arxiv_id":"1901.06212","n_code_links":2,"syntology":null},{"paper":null,"slug":"activation-functions-for-generalized-learning","title":"Activation Functions for Generalized Learning Vector Quantization - A Performance Comparison","date":"2019-01-17","arxiv_id":"1901.05995","n_code_links":0,"syntology":null},{"paper":"/paper/domain-adaptation-for-structured-output-via","slug":"domain-adaptation-for-structured-output-via","title":"Domain Adaptation for Structured Output via Discriminative Patch Representations","date":"2019-01-16","arxiv_id":"1901.05427","n_code_links":8,"syntology":{"ran":4,"of":4,"n_ran_checked":2,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"4 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["wasidennis/AdaptSegNet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"spectrogram-feature-losses-for-music-source","title":"Spectrogram Feature Losses for Music Source Separation","date":"2019-01-15","arxiv_id":"1901.05061","n_code_links":0,"syntology":null},{"paper":"/paper/transfer-learning-for-prosthetics-using","slug":"transfer-learning-for-prosthetics-using","title":"Transfer Learning for Prosthetics Using Imitation Learning","date":"2019-01-15","arxiv_id":"1901.04772","n_code_links":1,"syntology":null},{"paper":null,"slug":"gan-based-virtual-re-staining-a-promising","title":"GAN-based Virtual Re-Staining: A Promising Solution for Whole Slide Image Analysis","date":"2019-01-13","arxiv_id":"1901.04059","n_code_links":0,"syntology":null},{"paper":"/paper/automated-deep-photo-style-transfer","slug":"automated-deep-photo-style-transfer","title":"Automated Deep Photo Style Transfer","date":"2019-01-12","arxiv_id":"1901.03915","n_code_links":1,"syntology":null},{"paper":"/paper/upsnet-a-unified-panoptic-segmentation","slug":"upsnet-a-unified-panoptic-segmentation","title":"UPSNet: A Unified Panoptic Segmentation Network","date":"2019-01-12","arxiv_id":"1901.03784","n_code_links":1,"syntology":{"ran":3,"of":3,"n_ran_checked":1,"n_instrument":2,"unverified":0,"pointer_only":3,"phrase":"3 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; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["uber-research/UPSNet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/csgan-cyclic-synthesized-generative","slug":"csgan-cyclic-synthesized-generative","title":"CSGAN: Cyclic-Synthesized Generative Adversarial Networks for Image-to-Image Transformation","date":"2019-01-11","arxiv_id":"1901.03554","n_code_links":2,"syntology":null},{"paper":null,"slug":"deep-learning-for-ranking-response-surfaces","title":"Deep Learning for Ranking Response Surfaces with Applications to Optimal Stopping Problems","date":"2019-01-11","arxiv_id":"1901.03478","n_code_links":0,"syntology":null},{"paper":"/paper/fishnet-a-versatile-backbone-for-image-region","slug":"fishnet-a-versatile-backbone-for-image-region","title":"FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction","date":"2019-01-11","arxiv_id":"1901.03495","n_code_links":6,"syntology":null},{"paper":null,"slug":"hand-segmentation-and-fingertip-tracking-from","title":"Hand Segmentation and Fingertip Tracking from Depth Camera Images Using Deep Convolutional Neural Network and Multi-task SegNet","date":"2019-01-11","arxiv_id":"1901.03465","n_code_links":0,"syntology":null},{"paper":null,"slug":"low-precision-constant-parameter-cnn-on-fpga","title":"Low Precision Constant Parameter CNN on FPGA","date":"2019-01-11","arxiv_id":"1901.04969","n_code_links":0,"syntology":null},{"paper":null,"slug":"residual-pyramid-fcn-for-robust-follicle","title":"Residual Pyramid FCN for Robust Follicle Segmentation","date":"2019-01-11","arxiv_id":"1901.03760","n_code_links":0,"syntology":null},{"paper":"/paper/the-benefits-of-over-parameterization-at","slug":"the-benefits-of-over-parameterization-at","title":"The Benefits of Over-parameterization at Initialization in Deep ReLU Networks","date":"2019-01-11","arxiv_id":"1901.03611","n_code_links":1,"syntology":null},{"paper":null,"slug":"adversarial-pseudo-healthy-synthesis-needs","title":"Adversarial Pseudo Healthy Synthesis Needs Pathology Factorization","date":"2019-01-10","arxiv_id":"1901.07295","n_code_links":0,"syntology":null},{"paper":"/paper/equalizing-gender-biases-in-neural-machine","slug":"equalizing-gender-biases-in-neural-machine","title":"Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques","date":"2019-01-10","arxiv_id":"1901.03116","n_code_links":1,"syntology":null},{"paper":null,"slug":"on-the-turing-completeness-of-modern-neural","title":"On the Turing Completeness of Modern Neural Network Architectures","date":"2019-01-10","arxiv_id":"1901.03429","n_code_links":0,"syntology":null},{"paper":"/paper/region-proposal-by-guided-anchoring","slug":"region-proposal-by-guided-anchoring","title":"Region Proposal by Guided Anchoring","date":"2019-01-10","arxiv_id":"1901.03278","n_code_links":2,"syntology":null},{"paper":"/paper/retinamask-learning-to-predict-masks-improves","slug":"retinamask-learning-to-predict-masks-improves","title":"RetinaMask: Learning to predict masks improves state-of-the-art single-shot detection for free","date":"2019-01-10","arxiv_id":"1901.03353","n_code_links":53,"syntology":null},{"paper":null,"slug":"composite-shape-modeling-via-latent-space","title":"Composite Shape Modeling via Latent Space Factorization","date":"2019-01-09","arxiv_id":"1901.02968","n_code_links":0,"syntology":null},{"paper":"/paper/is-it-time-to-swish-comparing-deep-learning","slug":"is-it-time-to-swish-comparing-deep-learning","title":"Is it Time to Swish? Comparing Deep Learning Activation Functions Across NLP tasks","date":"2019-01-09","arxiv_id":"1901.02671","n_code_links":1,"syntology":null},{"paper":"/paper/transformer-xl-attentive-language-models","slug":"transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","arxiv_id":"1901.02860","n_code_links":37,"syntology":{"ran":67,"of":143,"n_ran_checked":49,"n_instrument":18,"unverified":76,"pointer_only":43,"phrase":"67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified","official":{"repos":["kimiyoung/transformer-xl"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":7,"n_ran_no_instrument_failure":7,"n_unverified":5,"ran_from_kinds":["listed","official","unlocated"]}}},{"paper":null,"slug":"3d-object-detection-using-scale-invariant-and","title":"3D Object Detection Using Scale Invariant and Feature Reweighting Networks","date":"2019-01-08","arxiv_id":"1901.02237","n_code_links":0,"syntology":null},{"paper":null,"slug":"collaborative-execution-of-deep-neural","title":"Collaborative Execution of Deep Neural Networks on Internet of Things Devices","date":"2019-01-08","arxiv_id":"1901.02537","n_code_links":0,"syntology":null},{"paper":"/paper/guidelines-and-benchmarks-for-deployment-of","slug":"guidelines-and-benchmarks-for-deployment-of","title":"Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time Apps","date":"2019-01-08","arxiv_id":"1901.02144","n_code_links":1,"syntology":null},{"paper":"/paper/panoptic-feature-pyramid-networks","slug":"panoptic-feature-pyramid-networks","title":"Panoptic Feature Pyramid Networks","date":"2019-01-08","arxiv_id":"1901.02446","n_code_links":12,"syntology":{"ran":11,"of":12,"n_ran_checked":4,"n_instrument":7,"unverified":1,"pointer_only":2,"phrase":"11 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; 7 where Syntology's instrument failed) · 1 unverified","official":{"repos":["facebookresearch/detectron2"],"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":"spatial-winograd-pruning-enabling-sparse","title":"Spatial-Winograd Pruning Enabling Sparse Winograd Convolution","date":"2019-01-08","arxiv_id":"1901.02132","n_code_links":0,"syntology":null},{"paper":"/paper/team-papelo-transformer-networks-at-fever","slug":"team-papelo-transformer-networks-at-fever","title":"Team Papelo: Transformer Networks at FEVER","date":"2019-01-08","arxiv_id":"1901.02534","n_code_links":1,"syntology":null},{"paper":"/paper/deeper-and-wider-siamese-networks-for-real","slug":"deeper-and-wider-siamese-networks-for-real","title":"Deeper and Wider Siamese Networks for Real-Time Visual Tracking","date":"2019-01-07","arxiv_id":"1901.01660","n_code_links":5,"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":["researchmm/SiamDW"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"dppnet-approximating-determinantal-point","title":"DPPNet: Approximating Determinantal Point Processes with Deep Networks","date":"2019-01-07","arxiv_id":"1901.02051","n_code_links":0,"syntology":null},{"paper":"/paper/dsconv-efficient-convolution-operator","slug":"dsconv-efficient-convolution-operator","title":"DSConv: Efficient Convolution Operator","date":"2019-01-07","arxiv_id":"1901.01928","n_code_links":1,"syntology":null},{"paper":"/paper/learning-based-optimization-of-the-under","slug":"learning-based-optimization-of-the-under","title":"Learning-based Optimization of the Under-sampling Pattern in MRI","date":"2019-01-07","arxiv_id":"1901.01960","n_code_links":1,"syntology":null},{"paper":"/paper/scale-aware-trident-networks-for-object","slug":"scale-aware-trident-networks-for-object","title":"Scale-Aware Trident Networks for Object Detection","date":"2019-01-07","arxiv_id":"1901.01892","n_code_links":4,"syntology":null},{"paper":null,"slug":"bandwidth-reduction-using-importance-weighted","title":"Bandwidth Reduction using Importance Weighted Pruning on Ring AllReduce","date":"2019-01-06","arxiv_id":"1901.01544","n_code_links":0,"syntology":null},{"paper":null,"slug":"channel-locality-block-a-variant-of-squeeze","title":"Channel Locality Block: A Variant of Squeeze-and-Excitation","date":"2019-01-06","arxiv_id":"1901.01493","n_code_links":0,"syntology":null},{"paper":"/paper/a-performance-comparison-of-loss-functions","slug":"a-performance-comparison-of-loss-functions","title":"A Performance Comparison of Loss Functions for Deep Face Recognition","date":"2019-01-01","arxiv_id":"1901.05903","n_code_links":1,"syntology":null},{"paper":null,"slug":"handwritten-indic-character-recognition-using","title":"Handwritten Indic Character Recognition using Capsule Networks","date":"2019-01-01","arxiv_id":"1901.00166","n_code_links":0,"syntology":null},{"paper":"/paper/lisht-non-parametric-linearly-scaled","slug":"lisht-non-parametric-linearly-scaled","title":"LiSHT: Non-Parametric Linearly Scaled Hyperbolic Tangent Activation Function for Neural Networks","date":"2019-01-01","arxiv_id":"1901.05894","n_code_links":2,"syntology":null},{"paper":"/paper/admm-nn-an-algorithm-hardware-co-design","slug":"admm-nn-an-algorithm-hardware-co-design","title":"ADMM-NN: An Algorithm-Hardware Co-Design Framework of DNNs Using Alternating Direction Method of Multipliers","date":"2018-12-31","arxiv_id":"1812.11677","n_code_links":1,"syntology":null},{"paper":"/paper/deep-residual-learning-in-the-jpeg-transform","slug":"deep-residual-learning-in-the-jpeg-transform","title":"Deep Residual Learning in the JPEG Transform Domain","date":"2018-12-31","arxiv_id":"1812.11690","n_code_links":1,"syntology":null},{"paper":null,"slug":"stealing-neural-networks-via-timing-side","title":"Stealing Neural Networks via Timing Side Channels","date":"2018-12-31","arxiv_id":"1812.11720","n_code_links":0,"syntology":null},{"paper":"/paper/impact-of-ground-truth-annotation-quality-on","slug":"impact-of-ground-truth-annotation-quality-on","title":"Impact of Ground Truth Annotation Quality on Performance of Semantic Image Segmentation of Traffic Conditions","date":"2018-12-30","arxiv_id":"1901.00001","n_code_links":1,"syntology":null},{"paper":null,"slug":"leishmaniasis-parasite-segmentation-and","title":"Leishmaniasis Parasite Segmentation and Classification using Deep Learning","date":"2018-12-30","arxiv_id":"1812.11586","n_code_links":0,"syntology":null},{"paper":"/paper/greedy-layerwise-learning-can-scale-to","slug":"greedy-layerwise-learning-can-scale-to","title":"Greedy Layerwise Learning Can Scale to ImageNet","date":"2018-12-29","arxiv_id":"1812.11446","n_code_links":1,"syntology":null},{"paper":null,"slug":"skeleton-transformer-networks-3d-human-pose","title":"Skeleton Transformer Networks: 3D Human Pose and Skinned Mesh from Single RGB Image","date":"2018-12-29","arxiv_id":"1812.11328","n_code_links":0,"syntology":null},{"paper":"/paper/studying-the-plasticity-in-deep-convolutional","slug":"studying-the-plasticity-in-deep-convolutional","title":"Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning","date":"2018-12-26","arxiv_id":"1812.10240","n_code_links":1,"syntology":null},{"paper":"/paper/deep-neural-networks-are-biased-towards","slug":"deep-neural-networks-are-biased-towards","title":"Random deep neural networks are biased towards simple functions","date":"2018-12-25","arxiv_id":"1812.10156","n_code_links":1,"syntology":null},{"paper":"/paper/residual-dense-network-for-image-restoration","slug":"residual-dense-network-for-image-restoration","title":"Residual Dense Network for Image Restoration","date":"2018-12-25","arxiv_id":"1812.10477","n_code_links":3,"syntology":null},{"paper":"/paper/dynamic-runtime-feature-map-pruning","slug":"dynamic-runtime-feature-map-pruning","title":"Dynamic Runtime Feature Map Pruning","date":"2018-12-24","arxiv_id":"1812.09922","n_code_links":1,"syntology":null},{"paper":"/paper/improving-mmd-gan-training-with-repulsive","slug":"improving-mmd-gan-training-with-repulsive","title":"Improving MMD-GAN Training with Repulsive Loss Function","date":"2018-12-24","arxiv_id":"1812.09916","n_code_links":1,"syntology":{"ran":7,"of":9,"n_ran_checked":7,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["richardwth/MMD-GAN"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"an-optical-frontend-for-a-convolutional","title":"An Optical Frontend for a Convolutional Neural Network","date":"2018-12-23","arxiv_id":"1901.03661","n_code_links":0,"syntology":null},{"paper":null,"slug":"fully-automatic-segmentation-of-sublingual","title":"Fully Automatic Segmentation of Sublingual Veins from Retrained U-Net Model for Few Near Infrared Images","date":"2018-12-22","arxiv_id":"1812.09477","n_code_links":0,"syntology":null},{"paper":"/paper/chamnet-towards-efficient-network-design","slug":"chamnet-towards-efficient-network-design","title":"ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation","date":"2018-12-21","arxiv_id":"1812.08934","n_code_links":1,"syntology":null},{"paper":"/paper/slimmable-neural-networks","slug":"slimmable-neural-networks","title":"Slimmable Neural Networks","date":"2018-12-21","arxiv_id":"1812.08928","n_code_links":4,"syntology":{"ran":2,"of":2,"n_ran_checked":2,"n_instrument":0,"unverified":0,"pointer_only":2,"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":["JiahuiYu/slimmable_networks"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/deepfakes-a-new-threat-to-face-recognition","slug":"deepfakes-a-new-threat-to-face-recognition","title":"DeepFakes: a New Threat to Face Recognition? Assessment and Detection","date":"2018-12-20","arxiv_id":"1812.08685","n_code_links":2,"syntology":null},{"paper":"/paper/dtmt-a-novel-deep-transition-architecture-for","slug":"dtmt-a-novel-deep-transition-architecture-for","title":"DTMT: A Novel Deep Transition Architecture for Neural Machine Translation","date":"2018-12-19","arxiv_id":"1812.07807","n_code_links":1,"syntology":null},{"paper":null,"slug":"fast-and-accurate-3d-medical-image","title":"Fast and Accurate 3D Medical Image Segmentation with Data-swapping Method","date":"2018-12-19","arxiv_id":"1812.07816","n_code_links":0,"syntology":null},{"paper":null,"slug":"multitask-painting-categorization-by-deep","title":"Multitask Painting Categorization by Deep Multibranch Neural Network","date":"2018-12-19","arxiv_id":"1812.08052","n_code_links":0,"syntology":null},{"paper":"/paper/rankgan-a-maximum-margin-ranking-gan-for","slug":"rankgan-a-maximum-margin-ranking-gan-for","title":"RankGAN: A Maximum Margin Ranking GAN for Generating Faces","date":"2018-12-19","arxiv_id":"1812.08196","n_code_links":1,"syntology":null},{"paper":null,"slug":"training-on-art-composition-attributes-to","title":"Training on Art Composition Attributes to Influence CycleGAN Art Generation","date":"2018-12-19","arxiv_id":"1812.07710","n_code_links":0,"syntology":null},{"paper":null,"slug":"sredgenet-edge-enhanced-single-image-super","title":"SREdgeNet: Edge Enhanced Single Image Super Resolution using Dense Edge Detection Network and Feature Merge Network","date":"2018-12-18","arxiv_id":"1812.07174","n_code_links":0,"syntology":null},{"paper":"/paper/decentralized-computation-offloading-for","slug":"decentralized-computation-offloading-for","title":"Decentralized Computation Offloading for Multi-User Mobile Edge Computing: A Deep Reinforcement Learning Approach","date":"2018-12-16","arxiv_id":"1812.07394","n_code_links":2,"syntology":null},{"paper":"/paper/trust-region-based-adversarial-attack-on","slug":"trust-region-based-adversarial-attack-on","title":"Trust Region Based Adversarial Attack on Neural Networks","date":"2018-12-16","arxiv_id":"1812.06371","n_code_links":2,"syntology":{"ran":7,"of":9,"n_ran_checked":0,"n_instrument":7,"unverified":2,"pointer_only":7,"phrase":"7 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; 7 where Syntology's instrument failed) · 2 unverified","official":{"repos":["amirgholami/trattack"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"a-low-effort-approach-to-structured-cnn","title":"A Low Effort Approach to Structured CNN Design Using PCA","date":"2018-12-15","arxiv_id":"1812.06224","n_code_links":0,"syntology":null},{"paper":"/paper/flatten-t-swish-a-thresholded-relu-swish-like","slug":"flatten-t-swish-a-thresholded-relu-swish-like","title":"Flatten-T Swish: a thresholded ReLU-Swish-like activation function for deep learning","date":"2018-12-15","arxiv_id":"1812.06247","n_code_links":2,"syntology":null},{"paper":"/paper/picanet-pixel-wise-contextual-attention","slug":"picanet-pixel-wise-contextual-attention","title":"PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detection","date":"2018-12-15","arxiv_id":"1812.06314","n_code_links":2,"syntology":null},{"paper":null,"slug":"automatic-quantification-of-the-lv-function","title":"Automatic quantification of the LV function and mass: a deep learning approach for cardiovascular MRI","date":"2018-12-14","arxiv_id":"1812.06061","n_code_links":0,"syntology":null},{"paper":null,"slug":"fast-mitochondria-segmentation-for","title":"Fast Mitochondria Detection for Connectomics","date":"2018-12-14","arxiv_id":"1812.06024","n_code_links":0,"syntology":null},{"paper":null,"slug":"products-of-many-large-random-matrices-and","title":"Products of Many Large Random Matrices and Gradients in Deep Neural Networks","date":"2018-12-14","arxiv_id":"1812.05994","n_code_links":0,"syntology":null},{"paper":null,"slug":"why-relu-units-sometimes-die-analysis-of","title":"Why ReLU Units Sometimes Die: Analysis of Single-Unit Error Backpropagation in Neural Networks","date":"2018-12-14","arxiv_id":"1812.05981","n_code_links":0,"syntology":null},{"paper":"/paper/dlow-domain-flow-for-adaptation-and","slug":"dlow-domain-flow-for-adaptation-and","title":"DLOW: Domain Flow for Adaptation and Generalization","date":"2018-12-13","arxiv_id":"1812.05418","n_code_links":1,"syntology":null},{"paper":"/paper/elastic-improving-cnns-with-instance-specific","slug":"elastic-improving-cnns-with-instance-specific","title":"ELASTIC: Improving CNNs with Dynamic Scaling Policies","date":"2018-12-13","arxiv_id":"1812.05262","n_code_links":1,"syntology":{"ran":3,"of":10,"n_ran_checked":2,"n_instrument":1,"unverified":7,"pointer_only":1,"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) · 7 unverified","official":{"repos":["allenai/elastic"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"nrityantar-pose-oblivious-indian-classical","title":"Nrityantar: Pose oblivious Indian classical dance sequence classification system","date":"2018-12-13","arxiv_id":"1812.05231","n_code_links":0,"syntology":null},{"paper":"/paper/soft-actor-critic-algorithms-and-applications","slug":"soft-actor-critic-algorithms-and-applications","title":"Soft Actor-Critic Algorithms and Applications","date":"2018-12-13","arxiv_id":"1812.05905","n_code_links":52,"syntology":{"ran":38,"of":40,"n_ran_checked":35,"n_instrument":3,"unverified":2,"pointer_only":5,"phrase":"38 ran (of which 0 constructed an object rather than computing a result; 35 with no instrument failure: 4 honoured, 1 violated, 30 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","official":{"repos":["rail-berkeley/softlearning"],"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/why-relu-networks-yield-high-confidence","slug":"why-relu-networks-yield-high-confidence","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","date":"2018-12-13","arxiv_id":"1812.05720","n_code_links":1,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","official":{"repos":["max-andr/relu_networks_overconfident"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official"]}}},{"paper":"/paper/cfun-combining-faster-r-cnn-and-u-net-network","slug":"cfun-combining-faster-r-cnn-and-u-net-network","title":"CFUN: Combining Faster R-CNN and U-net Network for Efficient Whole Heart Segmentation","date":"2018-12-12","arxiv_id":"1812.04914","n_code_links":1,"syntology":null},{"paper":"/paper/deep-anomaly-detection-with-outlier-exposure","slug":"deep-anomaly-detection-with-outlier-exposure","title":"Deep Anomaly Detection with Outlier Exposure","date":"2018-12-11","arxiv_id":"1812.04606","n_code_links":9,"syntology":{"ran":5,"of":5,"n_ran_checked":3,"n_instrument":2,"unverified":0,"pointer_only":4,"phrase":"5 ran (of which 2 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) · 0 unverified","official":{"repos":["hendrycks/outlier-exposure"],"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/deep-networks-with-probabilistic-gates","slug":"deep-networks-with-probabilistic-gates","title":"Channel selection using Gumbel Softmax","date":"2018-12-11","arxiv_id":"1812.04180","n_code_links":1,"syntology":null},{"paper":null,"slug":"hyperbolic-deep-learning-for-chinese-natural","title":"Hyperbolic Deep Learning for Chinese Natural Language Understanding","date":"2018-12-11","arxiv_id":"1812.10408","n_code_links":0,"syntology":null},{"paper":"/paper/layer-parallel-training-of-deep-residual","slug":"layer-parallel-training-of-deep-residual","title":"Layer-Parallel Training of Deep Residual Neural Networks","date":"2018-12-11","arxiv_id":"1812.04352","n_code_links":1,"syntology":null},{"paper":null,"slug":"accuracy-uncertainty-and-adaptability-of","title":"Accuracy, Uncertainty, and Adaptability of Automatic Myocardial ASL Segmentation using Deep CNN","date":"2018-12-10","arxiv_id":"1812.03974","n_code_links":0,"syntology":null},{"paper":"/paper/attention-guided-unified-network-for-panoptic","slug":"attention-guided-unified-network-for-panoptic","title":"Attention-guided Unified Network for Panoptic Segmentation","date":"2018-12-10","arxiv_id":"1812.03904","n_code_links":0,"syntology":null},{"paper":"/paper/global-deep-learning-methods-for","slug":"global-deep-learning-methods-for","title":"Non-local U-Net for Biomedical Image Segmentation","date":"2018-12-10","arxiv_id":"1812.04103","n_code_links":3,"syntology":null},{"paper":"/paper/learning-embedding-adaptation-for-few-shot","slug":"learning-embedding-adaptation-for-few-shot","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","date":"2018-12-10","arxiv_id":"1812.03664","n_code_links":6,"syntology":null},{"paper":null,"slug":"top-n-rank-a-scalable-list-wise-ranking","title":"Top-N-Rank: A Scalable List-wise Ranking Method for Recommender Systems","date":"2018-12-10","arxiv_id":"1812.04109","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-structured-model-for-action-detection","title":"A Structured Model For Action Detection","date":"2018-12-09","arxiv_id":"1812.03544","n_code_links":0,"syntology":null},{"paper":"/paper/fbnet-hardware-aware-efficient-convnet-design","slug":"fbnet-hardware-aware-efficient-convnet-design","title":"FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search","date":"2018-12-09","arxiv_id":"1812.03443","n_code_links":5,"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":["facebookresearch/mobile-vision"],"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":"generalized-batch-normalization-towards","title":"Generalized Batch Normalization: Towards Accelerating Deep Neural Networks","date":"2018-12-08","arxiv_id":"1812.03271","n_code_links":0,"syntology":null},{"paper":"/paper/spatial-temporal-person-re-identification","slug":"spatial-temporal-person-re-identification","title":"Spatial-Temporal Person Re-identification","date":"2018-12-08","arxiv_id":"1812.03282","n_code_links":3,"syntology":{"ran":8,"of":10,"n_ran_checked":8,"n_instrument":0,"unverified":2,"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) · 2 unverified","official":{"repos":["Wanggcong/Spatial-Temporal-Re-identification"],"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":["listed","official"]}}},{"paper":"/paper/variational-saccading-efficient-inference-for","slug":"variational-saccading-efficient-inference-for","title":"Variational Saccading: Efficient Inference for Large Resolution Images","date":"2018-12-08","arxiv_id":"1812.03170","n_code_links":1,"syntology":null},{"paper":null,"slug":"kernel-transformer-networks-for-compact","title":"Kernel Transformer Networks for Compact Spherical Convolution","date":"2018-12-07","arxiv_id":"1812.03115","n_code_links":0,"syntology":null},{"paper":"/paper/off-policy-deep-reinforcement-learning","slug":"off-policy-deep-reinforcement-learning","title":"Off-Policy Deep Reinforcement Learning without Exploration","date":"2018-12-07","arxiv_id":"1812.02900","n_code_links":10,"syntology":{"ran":14,"of":14,"n_ran_checked":14,"n_instrument":0,"unverified":0,"pointer_only":9,"phrase":"14 ran (of which 12 constructed an object rather than computing a result; 14 with no instrument failure: 1 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["sfujim/BCQ"],"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":"optimizing-speedaccuracy-trade-off-for-person","title":"Optimizing speed/accuracy trade-off for person re-identification via knowledge distillation","date":"2018-12-07","arxiv_id":"1812.02937","n_code_links":0,"syntology":null},{"paper":null,"slug":"shufflenasnets-efficient-cnn-models-through","title":"ShuffleNASNets: Efficient CNN models through modified Efficient Neural Architecture Search","date":"2018-12-07","arxiv_id":"1812.02975","n_code_links":0,"syntology":null},{"paper":null,"slug":"automatically-segmenting-the-left-atrium-from","title":"Automatically Segmenting the Left Atrium from Cardiac Images Using Successive 3D U-Nets and a Contour Loss","date":"2018-12-06","arxiv_id":"1812.02518","n_code_links":0,"syntology":null},{"paper":null,"slug":"dsnet-for-real-time-driving-scene-semantic","title":"DSNet for Real-Time Driving Scene Semantic Segmentation","date":"2018-12-06","arxiv_id":"1812.07049","n_code_links":0,"syntology":null}],"record_sha256":"40ed2146924fd4f07ab88cea67ecd243190f8615413290edd5b7971ffd238b88","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}