{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1703.01365","title":"Axiomatic Attribution for Deep Networks","created":"2017-03-04","cited_by_count":3384},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1704.02685","title":"Learning Important Features Through Propagating Activation Differences","created":"2017-04-10","cited_by_count":1458},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"1801.07606","title":"Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning","created":"2018-01-22","cited_by_count":1102},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1810.02244","title":"Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networks","created":"2018-10-04","cited_by_count":881},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"1701.04128","title":"Understanding the Effective Receptive Field in Deep Convolutional Neural Networks","created":"2017-01-15","cited_by_count":553},{"id":"1909.12223","title":"PairNorm: Tackling Oversmoothing in GNNs","created":"2019-09-26","cited_by_count":297},{"id":"1904.00760","title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","created":"2019-03-20","cited_by_count":260},{"id":"2012.02046","title":"Neural Prototype Trees for Interpretable Fine-grained Image Recognition","created":"2020-12-03","cited_by_count":214},{"id":"1702.04595","title":"Visualizing Deep Neural Network Decisions: Prediction Difference Analysis","created":"2017-02-15","cited_by_count":166},{"id":"2003.10477","title":"Distilling Knowledge from Graph Convolutional Networks","created":"2020-03-23","cited_by_count":129},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"1903.10992","title":"Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximation","created":"2019-03-26","cited_by_count":115},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115},{"id":"1812.10025","title":"Attention Branch Network: Learning of Attention Mechanism for Visual Explanation","created":"2018-12-25","cited_by_count":109},{"id":"2007.08558","title":"On Robustness and Transferability of Convolutional Neural Networks","created":"2020-07-16","cited_by_count":98},{"id":"2112.00911","title":"ProtGNN: Towards Self-Explaining Graph Neural Networks","created":"2021-12-02","cited_by_count":96},{"id":"2010.05421","title":"Factorizable Graph Convolutional Networks","created":"2020-10-12","cited_by_count":79},{"id":"2210.17409","title":"Deep Model Reassembly","created":"2022-10-24","cited_by_count":78},{"id":"2002.12247","title":"Learning Representations by Predicting Bags of Visual Words","created":"2020-02-27","cited_by_count":73},{"id":"2203.10202","title":"Relationformer: A Unified Framework for Image-to-Graph Generation","created":"2022-03-19","cited_by_count":67},{"id":"2105.02968","title":"This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networks","created":"2021-05-05","cited_by_count":65},{"id":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64},{"id":"2208.10431","title":"ProtoPFormer: Concentrating on Prototypical Parts in Vision Transformers for Interpretable Image Recognition","created":"2022-08-22","cited_by_count":63},{"id":"2209.09056","title":"Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off","created":"2022-09-19","cited_by_count":61},{"id":"2207.03337","title":"Factorizing Knowledge in Neural Networks","created":"2022-07-04","cited_by_count":59},{"id":"2006.09623","title":"Learning Visual Commonsense for Robust Scene Graph Generation","created":"2020-06-17","cited_by_count":47},{"id":"1802.05451","title":"Mapping Images to Scene Graphs with Permutation-Invariant Structured Prediction","created":"2018-02-15","cited_by_count":44},{"id":"2111.06236","title":"Discovering and Explaining the Representation Bottleneck of DNNs","created":"2021-11-11","cited_by_count":42},{"id":"2105.00290","title":"A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts","created":"2021-05-01","cited_by_count":33},{"id":"2207.11681","title":"Learning Graph Neural Networks for Image Style Transfer","created":"2022-07-24","cited_by_count":29},{"id":"2101.03464","title":"SPAGAN: Shortest Path Graph Attention Network","created":"2021-01-10","cited_by_count":28},{"id":"2109.12872","title":"Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks","created":"2021-09-27","cited_by_count":25},{"id":"1901.02413","title":"Interpretable CNNs for Object Classification","created":"2019-01-08","cited_by_count":17},{"id":"2112.04934","title":"Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers","created":"2021-12-09","cited_by_count":6},{"id":"2101.01239","title":"Explainable Neural Network-based Modulation Classification via Concept Bottleneck Models","created":"2021-01-04","cited_by_count":5},{"id":"2202.10701","title":"Bag of Visual Words (BoVW) with Deep Features -- Patch Classification Model for Limited Dataset of Breast Tumours","created":"2022-02-22","cited_by_count":2},{"id":"2110.10568","title":"Inference Graphs for CNN Interpretation","created":"2021-10-20","cited_by_count":1}],"next_cursor":null}