{"list":"other","total":57,"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"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":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1703.06211","title":"Deformable Convolutional Networks","created":"2017-03-17","cited_by_count":1488},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"1810.03292","title":"Sanity Checks for Saliency Maps","created":"2018-10-08","cited_by_count":1156},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1902.10186","title":"Attention is not Explanation","created":"2019-02-26","cited_by_count":929},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"2108.08810","title":"Do Vision Transformers See Like Convolutional Neural Networks?","created":"2021-08-19","cited_by_count":675},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"1909.11556","title":"Reducing Transformer Depth on Demand with Structured Dropout","created":"2019-09-25","cited_by_count":439},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"2112.07658","title":"AdaViT: Adaptive Tokens for Efficient Vision Transformer","created":"2021-12-14","cited_by_count":362},{"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":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285},{"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":"2210.13452","title":"MetaFormer Baselines for Vision","created":"2022-10-24","cited_by_count":132},{"id":"2111.15000","title":"Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes","created":"2021-11-29","cited_by_count":120},{"id":"2112.02902","title":"Interpretable Image Classification with Differentiable Prototypes Assignment","created":"2021-12-06","cited_by_count":97},{"id":"2210.11841","title":"Diffusion Visual Counterfactual Explanations","created":"2022-10-21","cited_by_count":96},{"id":"2205.10268","title":"B-cos Networks: Alignment is All We Need for Interpretability","created":"2022-05-20","cited_by_count":88},{"id":"2103.10619","title":"Scalable Vision Transformers with Hierarchical Pooling","created":"2021-03-19","cited_by_count":84},{"id":"2203.15636","title":"Diffusion Models for Counterfactual Explanations","created":"2022-03-29","cited_by_count":79},{"id":"1906.10651","title":"Interpretable Image Recognition with Hierarchical Prototypes","created":"2019-06-25","cited_by_count":65},{"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":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52},{"id":"2011.02863","title":"This Looks Like That, Because ... Explaining Prototypes for Interpretable Image Recognition","created":"2020-11-05","cited_by_count":50},{"id":"2303.09962","title":"Adversarial Counterfactual Visual Explanations","created":"2023-03-17","cited_by_count":47},{"id":"2301.04011","title":"Learning Support and Trivial Prototypes for Interpretable Image Classification","created":"2023-01-08","cited_by_count":38},{"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":"2306.10898","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","created":"2023-06-19","cited_by_count":31},{"id":"2106.10649","title":"CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliency","created":"2021-06-20","cited_by_count":28},{"id":"2211.12380","title":"OCTET: Object-aware Counterfactual Explanations","created":"2022-11-22","cited_by_count":28},{"id":"2007.08194","title":"Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters","created":"2020-07-16","cited_by_count":26},{"id":"2309.03173","title":"PDiscoNet: Semantically consistent part discovery for fine-grained recognition","created":"2023-09-06","cited_by_count":21},{"id":"2107.04474","title":"Interpretable Compositional Convolutional Neural Networks","created":"2021-07-09","cited_by_count":16},{"id":"2311.04157","title":"A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis","created":"2023-11-07","cited_by_count":15},{"id":"1801.08640","title":"Considerations When Learning Additive Explanations for Black-Box Models","created":"2018-01-26","cited_by_count":10},{"id":"2305.15775","title":"Concept-Centric Transformers: Enhancing Model Interpretability through Object-Centric Concept Learning within a Shared Global Workspace","created":"2023-05-25","cited_by_count":7}],"next_cursor":null}