{"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/kaiming-initialization/papers/28","list_of":"/method/kaiming-initialization","method":"Kaiming Initialization","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":28,"pages_in_order":30,"rows_per_page":100,"rows":[2701,2800],"of":2931,"counts":{"archive_papers_tagged":2931,"with_a_code_link":1332,"where_syntology_ran_a_sample":379,"not_listed_spam_title":0,"listed":2931,"listed_where_code_ran":379,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":319,"every_run_a_failure_of_syntologys_instrument":60,"listed_with_a_run_with_no_instrument_failure":319,"listed_every_run_a_failure_of_syntologys_instrument":60,"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/kaiming-initialization","prev":"/method/kaiming-initialization/papers/27","next":"/method/kaiming-initialization/papers/29","papers":[{"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":"treesegnet-adaptive-tree-cnns-for","title":"TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation","date":"2018-04-29","arxiv_id":"1804.10879","n_code_links":0,"syntology":null},{"paper":null,"slug":"spiking-deep-residual-network","title":"Spiking Deep Residual Network","date":"2018-04-28","arxiv_id":"1805.01352","n_code_links":0,"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":"iamnn-iterative-and-adaptive-mobile-neural","title":"IamNN: Iterative and Adaptive Mobile Neural Network for Efficient Image Classification","date":"2018-04-26","arxiv_id":"1804.10123","n_code_links":0,"syntology":null},{"paper":"/paper/learning-a-discriminative-feature-network-for","slug":"learning-a-discriminative-feature-network-for","title":"Learning a Discriminative Feature Network for Semantic Segmentation","date":"2018-04-25","arxiv_id":"1804.09337","n_code_links":3,"syntology":{"ran":3,"of":8,"n_ran_checked":3,"n_instrument":0,"unverified":5,"pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":null}},{"paper":null,"slug":"study-of-residual-networks-for-image","title":"Study of Residual Networks for Image Recognition","date":"2018-04-21","arxiv_id":"1805.00325","n_code_links":0,"syntology":null},{"paper":"/paper/simple-baselines-for-human-pose-estimation","slug":"simple-baselines-for-human-pose-estimation","title":"Simple Baselines for Human Pose Estimation and Tracking","date":"2018-04-17","arxiv_id":"1804.06208","n_code_links":27,"syntology":null},{"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/exfuse-enhancing-feature-fusion-for-semantic","slug":"exfuse-enhancing-feature-fusion-for-semantic","title":"ExFuse: Enhancing Feature Fusion for Semantic Segmentation","date":"2018-04-11","arxiv_id":"1804.03821","n_code_links":0,"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/markerless-tracking-of-user-defined-features","slug":"markerless-tracking-of-user-defined-features","title":"Markerless tracking of user-defined features with deep learning","date":"2018-04-09","arxiv_id":"1804.03142","n_code_links":1,"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":"/paper/look-into-person-joint-body-parsing-pose","slug":"look-into-person-joint-body-parsing-pose","title":"Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmark","date":"2018-04-05","arxiv_id":"1804.01984","n_code_links":3,"syntology":null},{"paper":"/paper/resnet-sparsifier-learning-strict-identity","slug":"resnet-sparsifier-learning-strict-identity","title":"Learning Strict Identity Mappings in Deep Residual Networks","date":"2018-04-05","arxiv_id":"1804.01661","n_code_links":1,"syntology":null},{"paper":null,"slug":"multilayer-complex-network-descriptors-for","title":"Multilayer Complex Network Descriptors for Color-Texture Characterization","date":"2018-04-02","arxiv_id":"1804.00501","n_code_links":0,"syntology":null},{"paper":null,"slug":"espnet-end-to-end-speech-processing-toolkit","title":"ESPnet: End-to-End Speech Processing Toolkit","date":"2018-03-30","arxiv_id":"1804.00015","n_code_links":0,"syntology":null},{"paper":"/paper/adaptive-affinity-fields-for-semantic","slug":"adaptive-affinity-fields-for-semantic","title":"Adaptive Affinity Fields for Semantic Segmentation","date":"2018-03-27","arxiv_id":"1803.10335","n_code_links":1,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":null}},{"paper":null,"slug":"incremental-training-of-deep-convolutional","title":"Incremental Training of Deep Convolutional Neural Networks","date":"2018-03-27","arxiv_id":"1803.10232","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-systematic-comparison-of-deep-learning","title":"A Systematic Comparison of Deep Learning Architectures in an Autonomous Vehicle","date":"2018-03-26","arxiv_id":"1803.09386","n_code_links":0,"syntology":null},{"paper":"/paper/context-encoding-for-semantic-segmentation","slug":"context-encoding-for-semantic-segmentation","title":"Context Encoding for Semantic Segmentation","date":"2018-03-23","arxiv_id":"1803.08904","n_code_links":12,"syntology":{"ran":6,"of":8,"n_ran_checked":5,"n_instrument":1,"unverified":2,"pointer_only":7,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":{"repos":["zhanghang1989/PyTorch-Encoding"],"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/group-normalization","slug":"group-normalization","title":"Group Normalization","date":"2018-03-22","arxiv_id":"1803.08494","n_code_links":22,"syntology":{"ran":7,"of":15,"n_ran_checked":5,"n_instrument":2,"unverified":8,"pointer_only":5,"phrase":"7 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 8 unverified","official":{"repos":["ppwwyyxx/GroupNorm-reproduce"],"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":["listed","official"]}}},{"paper":null,"slug":"adversarial-defense-based-on-structure-to","title":"Adversarial Defense based on Structure-to-Signal Autoencoders","date":"2018-03-21","arxiv_id":"1803.07994","n_code_links":0,"syntology":null},{"paper":null,"slug":"learning-and-recognizing-human-action-from","title":"Learning and Recognizing Human Action from Skeleton Movement with Deep Residual Neural Networks","date":"2018-03-21","arxiv_id":"1803.07780","n_code_links":0,"syntology":null},{"paper":"/paper/diagnostic-classification-of-lung-nodules","slug":"diagnostic-classification-of-lung-nodules","title":"Diagnostic Classification Of Lung Nodules Using 3D Neural Networks","date":"2018-03-19","arxiv_id":"1803.07192","n_code_links":2,"syntology":null},{"paper":"/paper/espnet-efficient-spatial-pyramid-of-dilated","slug":"espnet-efficient-spatial-pyramid-of-dilated","title":"ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation","date":"2018-03-19","arxiv_id":"1803.06815","n_code_links":8,"syntology":{"ran":9,"of":10,"n_ran_checked":7,"n_instrument":2,"unverified":1,"pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","official":{"repos":["sacmehta/ESPNet"],"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/seqface-make-full-use-of-sequence-information","slug":"seqface-make-full-use-of-sequence-information","title":"SeqFace: Make full use of sequence information for face recognition","date":"2018-03-17","arxiv_id":"1803.06524","n_code_links":1,"syntology":null},{"paper":"/paper/dynamic-structured-semantic-propagation","slug":"dynamic-structured-semantic-propagation","title":"Dynamic-structured Semantic Propagation Network","date":"2018-03-16","arxiv_id":"1803.06067","n_code_links":0,"syntology":null},{"paper":null,"slug":"studying-invariances-of-trained-convolutional","title":"Studying Invariances of Trained Convolutional Neural Networks","date":"2018-03-15","arxiv_id":"1803.05963","n_code_links":0,"syntology":null},{"paper":"/paper/averaging-weights-leads-to-wider-optima-and","slug":"averaging-weights-leads-to-wider-optima-and","title":"Averaging Weights Leads to Wider Optima and Better Generalization","date":"2018-03-14","arxiv_id":"1803.05407","n_code_links":17,"syntology":{"ran":7,"of":9,"n_ran_checked":5,"n_instrument":2,"unverified":2,"pointer_only":4,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified","official":{"repos":["timgaripov/swa"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/heneta-highly-efficient-convolutional-neural","slug":"heneta-highly-efficient-convolutional-neural","title":"HENet:A Highly Efficient Convolutional Neural Networks Optimized for Accuracy, Speed and Storage","date":"2018-03-07","arxiv_id":"1803.02742","n_code_links":1,"syntology":null},{"paper":"/paper/rtseg-real-time-semantic-segmentation","slug":"rtseg-real-time-semantic-segmentation","title":"RTSeg: Real-time Semantic Segmentation Comparative Study","date":"2018-03-07","arxiv_id":"1803.02758","n_code_links":2,"syntology":null},{"paper":null,"slug":"comparison-of-deep-learning-approaches-for","title":"Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification","date":"2018-03-06","arxiv_id":"1803.02315","n_code_links":0,"syntology":null},{"paper":null,"slug":"early-start-intention-detection-of-cyclists","title":"Early Start Intention Detection of Cyclists Using Motion History Images and a Deep Residual Network","date":"2018-03-06","arxiv_id":"1803.02242","n_code_links":0,"syntology":null},{"paper":null,"slug":"abnormality-detection-in-mammography-using","title":"Abnormality Detection in Mammography using Deep Convolutional Neural Networks","date":"2018-03-05","arxiv_id":"1803.01906","n_code_links":0,"syntology":null},{"paper":"/paper/path-aggregation-network-for-instance","slug":"path-aggregation-network-for-instance","title":"Path Aggregation Network for Instance Segmentation","date":"2018-03-05","arxiv_id":"1803.01534","n_code_links":10,"syntology":{"ran":3,"of":4,"n_ran_checked":2,"n_instrument":1,"unverified":1,"pointer_only":2,"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) · 1 unverified","official":{"repos":["ShuLiu1993/PANet"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"paper":"/paper/pose-robust-face-recognition-via-deep","slug":"pose-robust-face-recognition-via-deep","title":"Pose-Robust Face Recognition via Deep Residual Equivariant Mapping","date":"2018-03-02","arxiv_id":"1803.00839","n_code_links":1,"syntology":{"ran":13,"of":15,"n_ran_checked":12,"n_instrument":1,"unverified":2,"pointer_only":1,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","official":null}},{"paper":null,"slug":"recurrent-residual-module-for-fast-inference","title":"Recurrent Residual Module for Fast Inference in Videos","date":"2018-02-27","arxiv_id":"1802.09723","n_code_links":0,"syntology":null},{"paper":null,"slug":"functional-gradient-boosting-based-on","title":"Functional Gradient Boosting based on Residual Network Perception","date":"2018-02-25","arxiv_id":"1802.09031","n_code_links":0,"syntology":null},{"paper":null,"slug":"wide-compression-tensor-ring-nets","title":"Wide Compression: Tensor Ring Nets","date":"2018-02-25","arxiv_id":"1802.09052","n_code_links":0,"syntology":null},{"paper":"/paper/towards-principled-design-of-deep","slug":"towards-principled-design-of-deep","title":"Towards Principled Design of Deep Convolutional Networks: Introducing SimpNet","date":"2018-02-17","arxiv_id":"1802.06205","n_code_links":1,"syntology":null},{"paper":"/paper/spectral-normalization-for-generative","slug":"spectral-normalization-for-generative","title":"Spectral Normalization for Generative Adversarial Networks","date":"2018-02-16","arxiv_id":"1802.05957","n_code_links":38,"syntology":{"ran":25,"of":31,"n_ran_checked":21,"n_instrument":4,"unverified":6,"pointer_only":15,"phrase":"25 ran (of which 9 constructed an object rather than computing a result; 21 with no instrument failure: 0 honoured, 1 violated, 20 with no contract checked; 4 where Syntology's instrument failed) · 6 unverified","official":{"repos":["pfnet-research/sngan_projection"],"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","named_in_paper"]}}},{"paper":"/paper/cgans-with-projection-discriminator","slug":"cgans-with-projection-discriminator","title":"cGANs with Projection Discriminator","date":"2018-02-15","arxiv_id":"1802.05637","n_code_links":12,"syntology":{"ran":9,"of":9,"n_ran_checked":4,"n_instrument":5,"unverified":0,"pointer_only":6,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 2 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["crcrpar/pytorch.sngan_projection","pfnet-research/sngan_projection"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":"/paper/hydra-an-ensemble-of-convolutional-neural","slug":"hydra-an-ensemble-of-convolutional-neural","title":"Hydra: an Ensemble of Convolutional Neural Networks for Geospatial Land Classification","date":"2018-02-10","arxiv_id":"1802.03518","n_code_links":1,"syntology":null},{"paper":"/paper/shakedrop-regularization-for-deep-residual","slug":"shakedrop-regularization-for-deep-residual","title":"ShakeDrop Regularization for Deep Residual Learning","date":"2018-02-07","arxiv_id":"1802.02375","n_code_links":5,"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":["imenurok/ShakeDrop"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"universal-deep-neural-network-compression","title":"Universal Deep Neural Network Compression","date":"2018-02-07","arxiv_id":"1802.02271","n_code_links":0,"syntology":null},{"paper":"/paper/mixed-link-networks","slug":"mixed-link-networks","title":"Mixed Link Networks","date":"2018-02-06","arxiv_id":"1802.01808","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-robustness-of-neural-networks","slug":"evaluating-the-robustness-of-neural-networks","title":"Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach","date":"2018-01-31","arxiv_id":"1801.10578","n_code_links":1,"syntology":null},{"paper":"/paper/numerical-coordinate-regression-with","slug":"numerical-coordinate-regression-with","title":"Numerical Coordinate Regression with Convolutional Neural Networks","date":"2018-01-23","arxiv_id":"1801.07372","n_code_links":2,"syntology":null},{"paper":"/paper/fastnet","slug":"fastnet","title":"FastNet","date":"2018-01-17","arxiv_id":"1802.02186","n_code_links":1,"syntology":null},{"paper":"/paper/understanding-the-disharmony-between-dropout","slug":"understanding-the-disharmony-between-dropout","title":"Understanding the Disharmony between Dropout and Batch Normalization by Variance Shift","date":"2018-01-16","arxiv_id":"1801.05134","n_code_links":5,"syntology":null},{"paper":null,"slug":"application-of-a-semantic-segmentation","title":"Application of a semantic segmentation convolutional neural network for accurate automatic detection and mapping of solar photovoltaic arrays in aerial imagery","date":"2018-01-11","arxiv_id":"1801.04018","n_code_links":0,"syntology":null},{"paper":"/paper/moments-in-time-dataset-one-million-videos","slug":"moments-in-time-dataset-one-million-videos","title":"Moments in Time Dataset: one million videos for event understanding","date":"2018-01-09","arxiv_id":"1801.03150","n_code_links":4,"syntology":null},{"paper":"/paper/panoptic-segmentation","slug":"panoptic-segmentation","title":"Panoptic Segmentation","date":"2018-01-03","arxiv_id":"1801.00868","n_code_links":9,"syntology":null},{"paper":null,"slug":"a-tensor-analysis-on-dense-connectivity-via","title":"A Tensor Analysis on Dense Connectivity via Convolutional Arithmetic Circuits","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"enhancing-batch-normalized-convolutional","title":"Enhancing Batch Normalized Convolutional Networks using Displaced Rectifier Linear Units: A Systematic Comparative Study","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"gradients-explode-deep-networks-are-shallow","title":"Gradients explode - Deep Networks are shallow - ResNet explained","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"model-specialization-for-inference-via-end-to","title":"Model Specialization for Inference Via End-to-End Distillation, Pruning, and Cascades","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"on-the-generalization-effects-of-densenet","title":"On the Generalization Effects of DenseNet Model Structures","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"shakedrop-regularization","title":"ShakeDrop regularization","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"sparse-complementary-convolution-for","title":"Sparse-Complementary Convolution for Efficient Model Utilization on CNNs","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"tensor-contraction-regression-networks","title":"Tensor Contraction & Regression Networks","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":null,"slug":"variational-network-quantization","title":"Variational Network Quantization","date":"2018-01-01","arxiv_id":null,"n_code_links":0,"syntology":null},{"paper":"/paper/handwritten-bangla-character-recognition","slug":"handwritten-bangla-character-recognition","title":"Handwritten Bangla Character Recognition Using The State-of-Art Deep Convolutional Neural Networks","date":"2017-12-28","arxiv_id":"1712.09872","n_code_links":1,"syntology":null},{"paper":"/paper/rapid-adaptation-with-conditionally-shifted","slug":"rapid-adaptation-with-conditionally-shifted","title":"Rapid Adaptation with Conditionally Shifted Neurons","date":"2017-12-28","arxiv_id":"1712.09926","n_code_links":0,"syntology":null},{"paper":"/paper/adversarial-synthesis-learning-enables","slug":"adversarial-synthesis-learning-enables","title":"Adversarial Synthesis Learning Enables Segmentation Without Target Modality Ground Truth","date":"2017-12-20","arxiv_id":"1712.07695","n_code_links":1,"syntology":null},{"paper":"/paper/improving-generalization-performance-by","slug":"improving-generalization-performance-by","title":"Improving Generalization Performance by Switching from Adam to SGD","date":"2017-12-20","arxiv_id":"1712.07628","n_code_links":6,"syntology":null},{"paper":"/paper/on-the-effectiveness-of-least-squares","slug":"on-the-effectiveness-of-least-squares","title":"On the Effectiveness of Least Squares Generative Adversarial Networks","date":"2017-12-18","arxiv_id":"1712.06391","n_code_links":3,"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: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","official":{"repos":["xudonmao/LSGAN","xudonmao/improved_LSGAN"],"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":"the-exploding-gradient-problem-demystified","title":"The exploding gradient problem demystified - definition, prevalence, impact, origin, tradeoffs, and solutions","date":"2017-12-15","arxiv_id":"1712.05577","n_code_links":0,"syntology":null},{"paper":"/paper/masklab-instance-segmentation-by-refining","slug":"masklab-instance-segmentation-by-refining","title":"MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Features","date":"2017-12-13","arxiv_id":"1712.04837","n_code_links":0,"syntology":null},{"paper":null,"slug":"gradient-normalization-depth-based-decay-for","title":"Gradient Normalization & Depth Based Decay For Deep Learning","date":"2017-12-10","arxiv_id":"1712.03607","n_code_links":0,"syntology":null},{"paper":"/paper/adabatch-adaptive-batch-sizes-for-training","slug":"adabatch-adaptive-batch-sizes-for-training","title":"AdaBatch: Adaptive Batch Sizes for Training Deep Neural Networks","date":"2017-12-06","arxiv_id":"1712.02029","n_code_links":1,"syntology":null},{"paper":"/paper/learning-semantic-concepts-and-order-for","slug":"learning-semantic-concepts-and-order-for","title":"Learning Semantic Concepts and Order for Image and Sentence Matching","date":"2017-12-06","arxiv_id":"1712.02036","n_code_links":0,"syntology":null},{"paper":"/paper/cascade-r-cnn-delving-into-high-quality","slug":"cascade-r-cnn-delving-into-high-quality","title":"Cascade R-CNN: Delving into High Quality Object Detection","date":"2017-12-03","arxiv_id":"1712.00726","n_code_links":8,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["zhaoweicai/cascade-rcnn"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"paper":null,"slug":"towards-understanding-feedback-from","title":"Towards understanding feedback from supermassive black holes using convolutional neural networks","date":"2017-12-02","arxiv_id":"1712.00523","n_code_links":0,"syntology":null},{"paper":null,"slug":"probabilistic-adaptive-computation-time","title":"Probabilistic Adaptive Computation Time","date":"2017-12-01","arxiv_id":"1712.00386","n_code_links":0,"syntology":null},{"paper":"/paper/convolutional-networks-with-adaptive","slug":"convolutional-networks-with-adaptive","title":"Convolutional Networks with Adaptive Inference Graphs","date":"2017-11-30","arxiv_id":"1711.11503","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":null}},{"paper":"/paper/learning-spatio-temporal-representation-with","slug":"learning-spatio-temporal-representation-with","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","date":"2017-11-28","arxiv_id":"1711.10305","n_code_links":2,"syntology":null},{"paper":"/paper/can-spatiotemporal-3d-cnns-retrace-the","slug":"can-spatiotemporal-3d-cnns-retrace-the","title":"Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?","date":"2017-11-27","arxiv_id":"1711.09577","n_code_links":26,"syntology":{"ran":7,"of":8,"n_ran_checked":0,"n_instrument":7,"unverified":1,"pointer_only":3,"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) · 1 unverified","official":{"repos":["kenshohara/3D-ResNets-PyTorch"],"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":null,"slug":"recurrent-generative-adversarial-networks-for","title":"Recurrent Generative Adversarial Networks for Proximal Learning and Automated Compressive Image Recovery","date":"2017-11-27","arxiv_id":"1711.10046","n_code_links":0,"syntology":null},{"paper":"/paper/deep-extreme-cut-from-extreme-points-to","slug":"deep-extreme-cut-from-extreme-points-to","title":"Deep Extreme Cut: From Extreme Points to Object Segmentation","date":"2017-11-24","arxiv_id":"1711.09081","n_code_links":2,"syntology":null},{"paper":"/paper/deep-expander-networks-efficient-deep","slug":"deep-expander-networks-efficient-deep","title":"Deep Expander Networks: Efficient Deep Networks from Graph Theory","date":"2017-11-23","arxiv_id":"1711.08757","n_code_links":2,"syntology":null},{"paper":"/paper/an-analysis-of-scale-invariance-in-object-1","slug":"an-analysis-of-scale-invariance-in-object-1","title":"An Analysis of Scale Invariance in Object Detection - SNIP","date":"2017-11-22","arxiv_id":"1711.08189","n_code_links":0,"syntology":null},{"paper":"/paper/blockdrop-dynamic-inference-paths-in-residual","slug":"blockdrop-dynamic-inference-paths-in-residual","title":"BlockDrop: Dynamic Inference Paths in Residual Networks","date":"2017-11-22","arxiv_id":"1711.08393","n_code_links":1,"syntology":null},{"paper":"/paper/shift-a-zero-flop-zero-parameter-alternative","slug":"shift-a-zero-flop-zero-parameter-alternative","title":"Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions","date":"2017-11-22","arxiv_id":"1711.08141","n_code_links":2,"syntology":null},{"paper":"/paper/non-local-neural-networks","slug":"non-local-neural-networks","title":"Non-local Neural Networks","date":"2017-11-21","arxiv_id":"1711.07971","n_code_links":32,"syntology":{"ran":3,"of":4,"n_ran_checked":1,"n_instrument":2,"unverified":1,"pointer_only":4,"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) · 1 unverified","official":{"repos":["facebookresearch/video-nonlocal-net"],"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/light-head-r-cnn-in-defense-of-two-stage","slug":"light-head-r-cnn-in-defense-of-two-stage","title":"Light-Head R-CNN: In Defense of Two-Stage Object Detector","date":"2017-11-20","arxiv_id":"1711.07264","n_code_links":5,"syntology":null},{"paper":"/paper/single-shot-refinement-neural-network-for","slug":"single-shot-refinement-neural-network-for","title":"Single-Shot Refinement Neural Network for Object Detection","date":"2017-11-18","arxiv_id":"1711.06897","n_code_links":16,"syntology":null},{"paper":null,"slug":"apprentice-using-knowledge-distillation","title":"Apprentice: Using Knowledge Distillation Techniques To Improve Low-Precision Network Accuracy","date":"2017-11-15","arxiv_id":"1711.05852","n_code_links":0,"syntology":null},{"paper":"/paper/learning-deep-compositional-grammatical","slug":"learning-deep-compositional-grammatical","title":"AOGNets: Compositional Grammatical Architectures for Deep Learning","date":"2017-11-15","arxiv_id":"1711.05847","n_code_links":4,"syntology":{"ran":3,"of":8,"n_ran_checked":3,"n_instrument":0,"unverified":5,"pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified","official":{"repos":["iVMCL/AOGNets"],"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/squeeze-segnet-a-new-fast-deep-convolutional","slug":"squeeze-segnet-a-new-fast-deep-convolutional","title":"Squeeze-SegNet: A new fast Deep Convolutional Neural Network for Semantic Segmentation","date":"2017-11-15","arxiv_id":"1711.05491","n_code_links":1,"syntology":null},{"paper":"/paper/chexnet-radiologist-level-pneumonia-detection","slug":"chexnet-radiologist-level-pneumonia-detection","title":"CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning","date":"2017-11-14","arxiv_id":"1711.05225","n_code_links":47,"syntology":{"ran":29,"of":37,"n_ran_checked":24,"n_instrument":5,"unverified":8,"pointer_only":13,"phrase":"29 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 1 violated, 22 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified","official":null}},{"paper":"/paper/log-densenet-how-to-sparsify-a-densenet","slug":"log-densenet-how-to-sparsify-a-densenet","title":"Log-DenseNet: How to Sparsify a DenseNet","date":"2017-10-30","arxiv_id":"1711.00002","n_code_links":1,"syntology":null},{"paper":null,"slug":"beyond-finite-layer-neural-networks-bridging","title":"Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations","date":"2017-10-27","arxiv_id":"1710.10121","n_code_links":0,"syntology":null},{"paper":null,"slug":"multi-level-residual-networks-from-dynamical","title":"Multi-level Residual Networks from Dynamical Systems View","date":"2017-10-27","arxiv_id":"1710.10348","n_code_links":0,"syntology":null},{"paper":"/paper/mixup-beyond-empirical-risk-minimization","slug":"mixup-beyond-empirical-risk-minimization","title":"mixup: Beyond Empirical Risk Minimization","date":"2017-10-25","arxiv_id":"1710.09412","n_code_links":71,"syntology":{"ran":36,"of":47,"n_ran_checked":16,"n_instrument":20,"unverified":11,"pointer_only":15,"phrase":"36 ran (of which 5 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 20 where Syntology's instrument failed) · 11 unverified","official":{"repos":["facebookresearch/mixup-cifar10"],"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":"radnet-radiologist-level-accuracy-using-deep","title":"RADNET: Radiologist Level Accuracy using Deep Learning for HEMORRHAGE detection in CT Scans","date":"2017-10-13","arxiv_id":"1710.04934","n_code_links":0,"syntology":null},{"paper":null,"slug":"residual-connections-encourage-iterative","title":"Residual Connections Encourage Iterative Inference","date":"2017-10-13","arxiv_id":"1710.04773","n_code_links":0,"syntology":null},{"paper":null,"slug":"energy-efficient-amortized-inference-with","title":"Energy-efficient Amortized Inference with Cascaded Deep Classifiers","date":"2017-10-10","arxiv_id":"1710.03368","n_code_links":0,"syntology":null},{"paper":"/paper/gp-gan-gender-preserving-gan-for-synthesizing","slug":"gp-gan-gender-preserving-gan-for-synthesizing","title":"GP-GAN: Gender Preserving GAN for Synthesizing Faces from Landmarks","date":"2017-10-03","arxiv_id":"1710.00962","n_code_links":2,"syntology":null}],"record_sha256":"33c15da135aff0ae545783f5f078bb3a1fb48b4679364cbe240bc9317f2e63b3","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}