{"list":"other","total":60,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1605.07146","title":"Wide Residual Networks","created":"2016-05-23","cited_by_count":3070},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"id":"2411.15594","title":"A Survey on LLM-as-a-Judge","created":"2024-11-23","cited_by_count":1423},{"id":"2309.08600","title":"Sparse Autoencoders Find Highly Interpretable Features in Language Models","created":"2023-09-15","cited_by_count":1420},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"2209.10652","title":"Toy Models of Superposition","created":"2022-09-21","cited_by_count":971},{"id":"1704.05796","title":"Network Dissection: Quantifying Interpretability of Deep Visual Representations","created":"2017-04-19","cited_by_count":708},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"1912.13445","title":"Robust Aggregation for Federated Learning","created":"2019-12-31","cited_by_count":317},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178},{"id":"1611.07450","title":"Grad-CAM: Why did you say that?","created":"2016-11-22","cited_by_count":161},{"id":"2203.14960","title":"Domino: Discovering Systematic Errors with Cross-Modal Embeddings","created":"2022-03-24","cited_by_count":156},{"id":"2204.10965","title":"CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks","created":"2022-04-23","cited_by_count":147},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119},{"id":"2110.04301","title":"Salient ImageNet: How to discover spurious features in Deep Learning?","created":"2021-10-08","cited_by_count":114},{"id":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91},{"id":"2204.08040","title":"NICO++: Towards Better Benchmarking for Domain Generalization","created":"2022-04-17","cited_by_count":86},{"id":"2412.05276","title":"Sparse autoencoders reveal selective remapping of visual concepts during adaptation","created":"2024-12-06","cited_by_count":68},{"id":"1404.1869","title":"DenseNet: Implementing Efficient ConvNet Descriptor Pyramids","created":"2014-04-07","cited_by_count":66},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58},{"id":"2312.02974","title":"Describing Differences in Image Sets with Natural Language","created":"2023-12-05","cited_by_count":53},{"id":"2403.08632","title":"A Decade's Battle on Dataset Bias: Are We There Yet?","created":"2024-03-13","cited_by_count":47},{"id":"2405.02363","title":"LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model","created":"2024-05-03","cited_by_count":44},{"id":"2212.04871","title":"Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet","created":"2022-12-09","cited_by_count":41},{"id":"2411.16725","title":"$\\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models","created":"2024-11-23","cited_by_count":30},{"id":"2309.17430","title":"FACTS: First Amplify Correlations and Then Slice to Discover Bias","created":"2023-09-29","cited_by_count":26},{"id":"2310.18297","title":"Image Clustering Conditioned on Text Criteria","created":"2023-10-27","cited_by_count":26},{"id":"2412.01876","title":"Understanding Bias in Large-Scale Visual Datasets","created":"2024-12-02","cited_by_count":15},{"id":"2212.02648","title":"Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases","created":"2022-12-05","cited_by_count":13},{"id":"2204.04601","title":"Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention","created":"2022-04-10","cited_by_count":11},{"id":"2501.16751","title":"HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging","created":"2025-01-28","cited_by_count":11},{"id":"2309.02401","title":"Prototype-based Dataset Comparison","created":"2023-09-05","cited_by_count":9},{"id":"2507.12464","title":"CytoSAE: Interpretable Cell Embeddings for Hematology","created":"2025-07-16","cited_by_count":8},{"id":"2409.18055","title":"Visual Data Diagnosis and Debiasing with Concept Graphs","created":"2024-09-26","cited_by_count":6},{"id":"2503.18629","title":"Towards Human-Understandable Multi-Dimensional Concept Discovery","created":"2025-03-24","cited_by_count":4},{"id":"2407.01996","title":"ViG-Bias: Visually Grounded Bias Discovery and Mitigation","created":"2024-07-02","cited_by_count":2},{"id":"2507.15227","title":"Mammo-SAE: Interpreting Breast Cancer Concept Learning with Sparse Autoencoders","created":"2025-07-21","cited_by_count":2}],"next_cursor":null}