{"list":"other","total":69,"rows":[{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"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":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1901.07031","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","created":"2019-01-21","cited_by_count":1423},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"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":"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":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1711.10925","title":"Deep Image Prior","created":"2017-11-29","cited_by_count":1098},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1705.02315","title":"ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases","created":"2017-05-05","cited_by_count":972},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"1806.10574","title":"This Looks Like That: Deep Learning for Interpretable Image Recognition","created":"2018-06-27","cited_by_count":737},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"2210.10163","title":"MedCLIP: Contrastive Learning from Unpaired Medical Images and Text","created":"2022-10-18","cited_by_count":570},{"id":"2303.00915","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","created":"2023-03-02","cited_by_count":520},{"id":"2211.08411","title":"Large Language Models Struggle to Learn Long-Tail Knowledge","created":"2022-11-15","cited_by_count":458},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2102.09508","title":"Domain Adaptation for Medical Image Analysis: A Survey","created":"2021-02-18","cited_by_count":352},{"id":"2402.13178","title":"Benchmarking Retrieval-Augmented Generation for Medicine","created":"2024-02-20","cited_by_count":331},{"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":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285},{"id":"2003.09871","title":"COVID-Net: A Tailored Deep Convolutional Neural Network Design for Detection of COVID-19 Cases from Chest X-Ray Images","created":"2020-03-22","cited_by_count":264},{"id":"2010.05761","title":"The Risks of Invariant Risk Minimization","created":"2020-10-12","cited_by_count":262},{"id":"2012.15029","title":"VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations","created":"2020-12-30","cited_by_count":239},{"id":"1908.02288","title":"BCN20000: Dermoscopic Lesions in the Wild","created":"2019-08-06","cited_by_count":225},{"id":"2210.11466","title":"Surgical Fine-Tuning Improves Adaptation to Distribution Shifts","created":"2022-10-20","cited_by_count":205},{"id":"2003.13145","title":"Can AI help in screening Viral and COVID-19 pneumonia?","created":"2020-03-29","cited_by_count":200},{"id":"2110.14503","title":"Simple data balancing achieves competitive worst-group-accuracy","created":"2021-10-27","cited_by_count":178},{"id":"1603.08507","title":"Generating Visual Explanations","created":"2016-03-28","cited_by_count":158},{"id":"2107.10356","title":"Reading Race: AI Recognises Patient's Racial Identity In Medical Images","created":"2021-07-21","cited_by_count":156},{"id":"2104.07876","title":"Deep Stable Learning for Out-Of-Distribution Generalization","created":"2021-04-16","cited_by_count":153},{"id":"2111.00595","title":"TorchXRayVision: A library of chest X-ray datasets and models","created":"2021-10-31","cited_by_count":131},{"id":"2302.14042","title":"Knowledge-enhanced Visual-Language Pre-training on Chest Radiology Images","created":"2023-02-27","cited_by_count":128},{"id":"2212.05221","title":"REVEAL: Retrieval-Augmented Visual-Language Pre-Training with Multi-Source Multimodal Knowledge Memory","created":"2022-12-10","cited_by_count":123},{"id":"2007.00478","title":"PAD-UFES-20: a skin lesion dataset composed of patient data and clinical images collected from smartphones","created":"2020-07-01","cited_by_count":118},{"id":"2003.11597","title":"COVID-19 Image Data Collection","created":"2020-03-25","cited_by_count":101},{"id":"2210.03809","title":"Retrieval Augmented Visual Question Answering with Outside Knowledge","created":"2022-10-07","cited_by_count":94},{"id":"1511.02570","title":"Explicit Knowledge-based Reasoning for Visual Question Answering","created":"2015-11-09","cited_by_count":85},{"id":"2112.13906","title":"Does CLIP Benefit Visual Question Answering in the Medical Domain as Much as it Does in the General Domain?","created":"2021-12-27","cited_by_count":85},{"id":"2103.12308","title":"IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography","created":"2021-03-23","cited_by_count":72},{"id":"2202.06856","title":"Domain-Adjusted Regression or: ERM May Already Learn Features Sufficient for Out-of-Distribution Generalization","created":"2022-02-14","cited_by_count":69},{"id":"2109.04014","title":"Weakly-Supervised Visual-Retriever-Reader for Knowledge-based Question Answering","created":"2021-09-09","cited_by_count":50},{"id":"2301.09819","title":"Model Agnostic Sample Reweighting for Out-of-Distribution Learning","created":"2023-01-24","cited_by_count":44},{"id":"2310.03182","title":"Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models","created":"2023-10-04","cited_by_count":40},{"id":"1911.02683","title":"Shaping Visual Representations with Language for Few-shot Classification","created":"2019-11-06","cited_by_count":27},{"id":"2202.02832","title":"Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification","created":"2022-02-06","cited_by_count":23},{"id":"2302.12343","title":"CHiLL: Zero-shot Custom Interpretable Feature Extraction from Clinical Notes with Large Language Models","created":"2023-02-23","cited_by_count":15},{"id":"2403.05606","title":"A Concept-based Interpretable Model for the Diagnosis of Choroid Neoplasias using Multimodal Data","created":"2024-03-08","cited_by_count":4}],"next_cursor":null}