{"list":"other","total":67,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1902.10811","title":"Do ImageNet Classifiers Generalize to ImageNet?","created":"2019-02-13","cited_by_count":1515},{"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":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2002.08546","title":"Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation","created":"2020-02-20","cited_by_count":848},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2103.02503","title":"Domain Generalization: A Survey","created":"2021-03-03","cited_by_count":764},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"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":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"1904.05046","title":"Generalizing from a Few Examples: A Survey on Few-Shot Learning","created":"2019-04-10","cited_by_count":463},{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382},{"id":"2205.12548","title":"RLPrompt: Optimizing Discrete Text Prompts with Reinforcement Learning","created":"2022-05-25","cited_by_count":366},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"id":"2303.15361","title":"A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts","created":"2023-03-27","cited_by_count":359},{"id":"2205.14865","title":"Prompt-aligned Gradient for Prompt Tuning","created":"2022-05-30","cited_by_count":341},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"2205.03340","title":"Prompt Distribution Learning","created":"2022-05-06","cited_by_count":235},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2210.07225","title":"Unified Vision and Language Prompt Learning","created":"2022-10-13","cited_by_count":148},{"id":"2204.03649","title":"Unsupervised Prompt Learning for Vision-Language Models","created":"2022-04-07","cited_by_count":127},{"id":"2008.01392","title":"Learning Visual Representations with Caption Annotations","created":"2020-08-04","cited_by_count":123},{"id":"2211.10277","title":"Task Residual for Tuning Vision-Language Models","created":"2022-11-18","cited_by_count":123},{"id":"2203.02664","title":"Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformers","created":"2022-03-05","cited_by_count":118},{"id":"1912.03432","title":"Improved Few-Shot Visual Classification","created":"2019-12-07","cited_by_count":115},{"id":"2106.09707","title":"Learning to Predict Visual Attributes in the Wild","created":"2021-06-17","cited_by_count":96},{"id":"2301.06267","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","created":"2023-01-16","cited_by_count":91},{"id":"1506.00511","title":"Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions","created":"2015-06-01","cited_by_count":64},{"id":"2210.01253","title":"PLOT: Prompt Learning with Optimal Transport for Vision-Language Models","created":"2022-10-03","cited_by_count":64},{"id":"2203.00048","title":"Multi-modal Alignment using Representation Codebook","created":"2022-02-28","cited_by_count":63},{"id":"2303.02995","title":"HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention","created":"2023-03-06","cited_by_count":44},{"id":"1705.08631","title":"Self-supervised learning of visual features through embedding images into text topic spaces","created":"2017-05-24","cited_by_count":43},{"id":"2112.02399","title":"VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts","created":"2021-12-04","cited_by_count":42},{"id":"2210.03794","title":"SVL-Adapter: Self-Supervised Adapter for Vision-Language Pretrained Models","created":"2022-10-07","cited_by_count":34},{"id":"2210.04287","title":"Learning to Decompose Visual Features with Latent Textual Prompts","created":"2022-10-09","cited_by_count":28},{"id":"2002.00169","title":"Deep Multi-View Enhancement Hashing for Image Retrieval","created":"2020-02-01","cited_by_count":27},{"id":"2007.10573","title":"Domain Generalization via Optimal Transport with Metric Similarity Learning","created":"2020-07-21","cited_by_count":27},{"id":"2112.09331","title":"Contrastive Vision-Language Pre-training with Limited Resources","created":"2021-12-17","cited_by_count":25},{"id":"2203.00242","title":"Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment","created":"2022-03-01","cited_by_count":23},{"id":"2303.00914","title":"Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation","created":"2023-03-02","cited_by_count":23},{"id":"1804.04314","title":"A Large-scale Attribute Dataset for Zero-shot Learning","created":"2018-04-12","cited_by_count":21},{"id":"2302.14794","title":"Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning","created":"2023-02-28","cited_by_count":20},{"id":"2303.11180","title":"Self-Correctable and Adaptable Inference for Generalizable Human Pose Estimation","created":"2023-03-20","cited_by_count":7},{"id":"1604.00326","title":"How to Transfer? Zero-Shot Object Recognition via Hierarchical Transfer of Semantic Attributes","created":"2016-04-01","cited_by_count":3}],"next_cursor":null}