{"list":"other","total":53,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2106.01946","title":"Convex optimization","created":"2021-06-03","cited_by_count":2515},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1806.07421","title":"RISE: Randomized Input Sampling for Explanation of Black-box Models","created":"2018-06-19","cited_by_count":838},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2210.07183","title":"Visual Classification via Description from Large Language Models","created":"2022-10-13","cited_by_count":336},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","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":"2211.11158","title":"Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification","created":"2022-11-21","cited_by_count":312},{"id":"2004.04581","title":"Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation","created":"2020-04-09","cited_by_count":300},{"id":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"2103.05677","title":"SMIL: Multimodal Learning with Severely Missing Modality","created":"2021-03-09","cited_by_count":245},{"id":"2005.00631","title":"Evaluating and Aggregating Feature-based Model Explanations","created":"2020-05-01","cited_by_count":188},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181},{"id":"1905.08883","title":"Explainable Machine Learning for Scientific Insights and Discoveries","created":"2019-05-21","cited_by_count":166},{"id":"2212.00638","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models","created":"2022-12-01","cited_by_count":150},{"id":"1909.13584","title":"Interpretations are useful: penalizing explanations to align neural networks with prior knowledge","created":"2019-09-30","cited_by_count":145},{"id":"2001.00396","title":"Restricting the Flow: Information Bottlenecks for Attribution","created":"2020-01-02","cited_by_count":110},{"id":"2112.00933","title":"PartImageNet: A Large, High-Quality Dataset of Parts","created":"2021-12-02","cited_by_count":107},{"id":"2204.14095","title":"PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining","created":"2022-04-29","cited_by_count":104},{"id":"2011.12854","title":"Right for the Right Concept: Revising Neuro-Symbolic Concepts by Interacting with their Explanations","created":"2020-11-25","cited_by_count":94},{"id":"2209.15517","title":"Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study","created":"2022-09-30","cited_by_count":66},{"id":"1905.09957","title":"Robust Attribution Regularization","created":"2019-05-23","cited_by_count":47},{"id":"2204.13091","title":"Attention Consistency on Visual Corruptions for Single-Source Domain Generalization","created":"2022-04-27","cited_by_count":37},{"id":"2012.12352","title":"Seeing past words: Testing the cross-modal capabilities of pretrained V&L models on counting tasks","created":"2020-12-22","cited_by_count":34},{"id":"1811.04896","title":"TED: Teaching AI to Explain its Decisions","created":"2018-11-12","cited_by_count":33},{"id":"2110.00527","title":"Consistent Explanations by Contrastive Learning","created":"2021-10-01","cited_by_count":18},{"id":"2303.16390","title":"Are Data-driven Explanations Robust against Out-of-distribution Data?","created":"2023-03-29","cited_by_count":14},{"id":"2204.05393","title":"Improving Few-Shot Part Segmentation using Coarse Supervision","created":"2022-04-11","cited_by_count":10},{"id":"2407.04949","title":"Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients","created":"2024-07-06","cited_by_count":7},{"id":"2112.09668","title":"Deep Learning for Spatiotemporal Modeling of Urbanization","created":"2021-12-17","cited_by_count":5}],"next_cursor":null}