{"list":"other","total":56,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2010.03759","title":"Energy-based Out-of-distribution Detection","created":"2020-10-08","cited_by_count":1299},{"id":"1710.03740","title":"Mixed Precision Training","created":"2017-10-10","cited_by_count":1156},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2106.02034","title":"DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification","created":"2021-06-03","cited_by_count":864},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"2110.00476","title":"ResNet strikes back: An improved training procedure in timm","created":"2021-10-01","cited_by_count":368},{"id":"1406.6247","title":"Recurrent Models of Visual Attention","created":"2014-06-24","cited_by_count":349},{"id":"2006.09994","title":"Noise or Signal: The Role of Image Backgrounds in Object Recognition","created":"2020-06-17","cited_by_count":343},{"id":"1703.03717","title":"Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations","created":"2017-03-10","cited_by_count":294},{"id":"1404.5997","title":"One weird trick for parallelizing convolutional neural networks","created":"2014-04-23","cited_by_count":264},{"id":"1802.07814","title":"Learning to Explain: An Information-Theoretic Perspective on Model Interpretation","created":"2018-02-21","cited_by_count":248},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232},{"id":"2011.12945","title":"No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems","created":"2020-11-25","cited_by_count":209},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"2106.04533","title":"Chasing Sparsity in Vision Transformers: An End-to-End Exploration","created":"2021-06-08","cited_by_count":183},{"id":"2401.10815","title":"Exploring scalable medical image encoders beyond text supervision","created":"2024-01-19","cited_by_count":132},{"id":"2201.08371","title":"Revisiting Weakly Supervised Pre-Training of Visual Perception Models","created":"2022-01-20","cited_by_count":116},{"id":"2401.08541","title":"Scalable Pre-training of Large Autoregressive Image Models","created":"2024-01-16","cited_by_count":115},{"id":"1905.01298","title":"SCOPS: Self-Supervised Co-Part Segmentation","created":"2019-05-03","cited_by_count":100},{"id":"2212.04825","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","created":"2022-12-09","cited_by_count":85},{"id":"2202.06523","title":"MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts","created":"2022-02-14","cited_by_count":81},{"id":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71},{"id":"2411.18704","title":"Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits","created":"2024-11-27","cited_by_count":71},{"id":"2111.14338","title":"Improving Deep Learning Interpretability by Saliency Guided Training","created":"2021-11-29","cited_by_count":68},{"id":"2210.00055","title":"MaskTune: Mitigating Spurious Correlations by Forcing to Explore","created":"2022-09-30","cited_by_count":66},{"id":"2212.07834","title":"Unsupervised Object Localization: Observing the Background to Discover Objects","created":"2022-12-15","cited_by_count":66},{"id":"2308.01045","title":"Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation","created":"2023-08-02","cited_by_count":62},{"id":"2206.07990","title":"Patch-level Representation Learning for Self-supervised Vision Transformers","created":"2022-06-16","cited_by_count":60},{"id":"2103.01890","title":"Have We Learned to Explain?: How Interpretability Methods Can Learn to Encode Predictions in their Interpretations","created":"2021-03-02","cited_by_count":59},{"id":"2211.03064","title":"ViT-CX: Causal Explanation of Vision Transformers","created":"2022-11-06","cited_by_count":28},{"id":"2309.03173","title":"PDiscoNet: Semantically consistent part discovery for fine-grained recognition","created":"2023-09-06","cited_by_count":21},{"id":"2303.03052","title":"Masked Images Are Counterfactual Samples for Robust Fine-tuning","created":"2023-03-06","cited_by_count":20},{"id":"2403.14552","title":"Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer","created":"2024-03-21","cited_by_count":19},{"id":"2404.01415","title":"On the Faithfulness of Vision Transformer Explanations","created":"2024-04-01","cited_by_count":19},{"id":"1706.04313","title":"Teaching Compositionality to CNNs","created":"2017-06-14","cited_by_count":18},{"id":"2402.18919","title":"Decompose-and-Compose: A Compositional Approach to Mitigating Spurious Correlation","created":"2024-02-29","cited_by_count":18},{"id":"2303.13755","title":"Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers","created":"2023-03-24","cited_by_count":16},{"id":"2309.06891","title":"Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?","created":"2023-09-13","cited_by_count":16},{"id":"2210.05832","title":"SaiT: Sparse Vision Transformers through Adaptive Token Pruning","created":"2022-10-11","cited_by_count":15},{"id":"2209.02869","title":"Interpretations Steered Network Pruning via Amortized Inferred Saliency Maps","created":"2022-09-07","cited_by_count":11},{"id":"2308.12127","title":"Masking Strategies for Background Bias Removal in Computer Vision Models","created":"2023-08-23","cited_by_count":9},{"id":"2407.04538","title":"PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers","created":"2024-07-05","cited_by_count":9},{"id":"2010.09750","title":"Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability","created":"2020-10-19","cited_by_count":7},{"id":"2409.18055","title":"Visual Data Diagnosis and Debiasing with Concept Graphs","created":"2024-09-26","cited_by_count":6},{"id":"2407.19308","title":"Comprehensive Attribution: Inherently Explainable Vision Model with Feature Detector","created":"2024-07-27","cited_by_count":5},{"id":"2306.12673","title":"Identifying and Disentangling Spurious Features in Pretrained Image Representations","created":"2023-06-22","cited_by_count":3},{"id":"2411.02664","title":"Explanations that reveal all through the definition of encoding","created":"2024-11-04","cited_by_count":3},{"id":"2406.08859","title":"Fusion of regional and sparse attention in Vision Transformers","created":"2024-06-13","cited_by_count":2}],"next_cursor":null}