{"list":"other","total":77,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"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":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"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":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1412.6806","title":"Striving for Simplicity: The All Convolutional Net","created":"2014-12-21","cited_by_count":990},{"id":"1905.09418","title":"Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned","created":"2019-05-23","cited_by_count":856},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"1910.01279","title":"Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks","created":"2019-10-03","cited_by_count":582},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2006.07159","title":"Are we done with ImageNet?","created":"2020-06-12","cited_by_count":333},{"id":"1608.00507","title":"Top-down Neural Attention by Excitation Backprop","created":"2016-08-01","cited_by_count":321},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303},{"id":"1605.01713","title":"Not Just a Black Box: Learning Important Features Through Propagating Activation Differences","created":"2016-05-05","cited_by_count":297},{"id":"1512.02479","title":"Explaining NonLinear Classification Decisions with Deep Taylor Decomposition","created":"2015-12-08","cited_by_count":250},{"id":"1905.00780","title":"Full-Gradient Representation for Neural Network Visualization","created":"2019-05-02","cited_by_count":191},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152},{"id":"2008.02312","title":"Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs","created":"2020-08-05","cited_by_count":151},{"id":"2405.07992","title":"MambaOut: Do We Really Need Mamba for Vision?","created":"2024-05-13","cited_by_count":143},{"id":"2209.11326","title":"Towards Faithful Model Explanation in NLP: A Survey","created":"2022-09-22","cited_by_count":130},{"id":"1902.03751","title":"Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded","created":"2019-02-11","cited_by_count":128},{"id":"2402.05602","title":"AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformers","created":"2024-02-08","cited_by_count":120},{"id":"1908.04211","title":"On Identifiability in Transformers","created":"2019-08-12","cited_by_count":116},{"id":"2202.07304","title":"XAI for Transformers: Better Explanations through Conservative Propagation","created":"2022-02-15","cited_by_count":100},{"id":"2204.00008","title":"Improving Adversarial Transferability via Neuron Attribution-Based Attacks","created":"2022-03-31","cited_by_count":93},{"id":"2011.08891","title":"Use HiResCAM instead of Grad-CAM for faithful explanations of convolutional neural networks","created":"2020-11-17","cited_by_count":79},{"id":"2203.04212","title":"Measuring the Mixing of Contextual Information in the Transformer","created":"2022-03-08","cited_by_count":65},{"id":"1611.07270","title":"Investigating the influence of noise and distractors on the interpretation of neural networks","created":"2016-11-22","cited_by_count":54},{"id":"2109.07152","title":"Incorporating Residual and Normalization Layers into Analysis of Masked Language Models","created":"2021-09-15","cited_by_count":51},{"id":"2308.06248","title":"FunnyBirds: A Synthetic Vision Dataset for a Part-Based Analysis of Explainable AI Methods","created":"2023-08-11","cited_by_count":50},{"id":"1906.03499","title":"ML-LOO: Detecting Adversarial Examples with Feature Attribution","created":"2019-06-08","cited_by_count":48},{"id":"2203.08008","title":"Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement","created":"2022-03-15","cited_by_count":48},{"id":"2206.05282","title":"Learning to Estimate Shapley Values with Vision Transformers","created":"2022-06-10","cited_by_count":45},{"id":"2205.03286","title":"GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers","created":"2022-05-06","cited_by_count":44},{"id":"2206.01161","title":"Optimizing Relevance Maps of Vision Transformers Improves Robustness","created":"2022-06-02","cited_by_count":41},{"id":"2205.13152","title":"Transferable Adversarial Attack based on Integrated Gradients","created":"2022-05-26","cited_by_count":35},{"id":"2206.06219","title":"Making Sense of Dependence: Efficient Black-box Explanations Using Dependence Measure","created":"2022-06-13","cited_by_count":33},{"id":"2304.05538","title":"ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification","created":"2023-04-11","cited_by_count":33},{"id":"2301.08110","title":"AtMan: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation","created":"2023-01-19","cited_by_count":31},{"id":"1908.04351","title":"Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation","created":"2019-08-06","cited_by_count":29},{"id":"2211.03064","title":"ViT-CX: Causal Explanation of Vision Transformers","created":"2022-11-06","cited_by_count":28},{"id":"2401.06654","title":"Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarks","created":"2024-01-12","cited_by_count":28},{"id":"2204.04908","title":"No Token Left Behind: Explainability-Aided Image Classification and Generation","created":"2022-04-11","cited_by_count":25},{"id":"1712.06957","title":"MURA: Large Dataset for Abnormality Detection in Musculoskeletal Radiographs","created":"2017-12-11","cited_by_count":20},{"id":"2203.08991","title":"AdapLeR: Speeding up Inference by Adaptive Length Reduction","created":"2022-03-16","cited_by_count":19},{"id":"2403.14552","title":"Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer","created":"2024-03-21","cited_by_count":19},{"id":"2402.18919","title":"Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation","created":"2024-02-29","cited_by_count":18},{"id":"2109.04236","title":"ECQ$^{\\text{x}}$: Explainability-Driven Quantization for Low-Bit and Sparse DNNs","created":"2021-09-09","cited_by_count":15},{"id":"2205.01929","title":"Explain to Not Forget: Defending Against Catastrophic Forgetting with XAI","created":"2022-05-04","cited_by_count":7},{"id":"2302.03318","title":"PAMI: partition input and aggregate outputs for model interpretation","created":"2023-02-07","cited_by_count":2}],"next_cursor":null}