{"list":"other","total":85,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"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":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"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":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"1710.03463","title":"Learning to Generalize: Meta-Learning for Domain Generalization","created":"2017-10-10","cited_by_count":763},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2110.07602","title":"P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks","created":"2021-10-14","cited_by_count":689},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"1805.12018","title":"Generalizing to Unseen Domains via Adversarial Data Augmentation","created":"2018-05-30","cited_by_count":451},{"id":"1903.06864","title":"Domain Generalization by Solving Jigsaw Puzzles","created":"2019-03-16","cited_by_count":450},{"id":"2102.08604","title":"SWAD: Domain Generalization by Seeking Flat Minima","created":"2021-02-17","cited_by_count":434},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"2307.06948","title":"Self-regulating Prompts: Foundational Model Adaptation without Forgetting","created":"2023-07-13","cited_by_count":272},{"id":"1703.04394","title":"Zero-Shot Learning -- The Good, the Bad and the Ugly","created":"2017-03-13","cited_by_count":255},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164},{"id":"2212.00638","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models","created":"2022-12-01","cited_by_count":150},{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148},{"id":"2110.10832","title":"Ensemble of Averages: Improving Model Selection and Boosting Performance in Domain Generalization","created":"2021-10-21","cited_by_count":144},{"id":"2202.05441","title":"Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs","created":"2022-02-11","cited_by_count":144},{"id":"2003.12815","title":"Efficient Domain Generalization via Common-Specific Low-Rank Decomposition","created":"2020-03-28","cited_by_count":134},{"id":"2208.08984","title":"Open-Vocabulary Universal Image Segmentation with MaskCLIP","created":"2022-08-18","cited_by_count":132},{"id":"1901.11448","title":"Feature-Critic Networks for Heterogeneous Domain Generalization","created":"2019-01-31","cited_by_count":130},{"id":"2008.12839","title":"Learning to Balance Specificity and Invariance for In and Out of Domain Generalization","created":"2020-08-28","cited_by_count":128},{"id":"1708.01471","title":"Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering","created":"2017-08-04","cited_by_count":117},{"id":"2210.14707","title":"Is Out-of-Distribution Detection Learnable?","created":"2022-10-26","cited_by_count":109},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97},{"id":"2302.00864","title":"CLIPood: Generalizing CLIP to Out-of-Distributions","created":"2023-02-02","cited_by_count":96},{"id":"1708.03619","title":"Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering","created":"2017-08-10","cited_by_count":79},{"id":"1803.04899","title":"Optimal Transport for Multi-source Domain Adaptation under Target Shift","created":"2018-03-13","cited_by_count":68},{"id":"2309.07439","title":"DePT: Decoupled Prompt Tuning","created":"2023-09-14","cited_by_count":58},{"id":"1907.08375","title":"Open Set Domain Adaptation: Theoretical Bound and Algorithm","created":"2019-07-19","cited_by_count":48},{"id":"2403.01849","title":"One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models","created":"2024-03-04","cited_by_count":48},{"id":"2403.14774","title":"Few-Shot Adversarial Prompt Learning on Vision-Language Models","created":"2024-03-21","cited_by_count":39},{"id":"2106.06196","title":"CausalAdv: Adversarial Robustness through the Lens of Causality","created":"2021-06-11","cited_by_count":37},{"id":"2304.11327","title":"Understanding and Improving Feature Learning for Out-of-Distribution Generalization","created":"2023-04-22","cited_by_count":35},{"id":"2004.12070","title":"Deep Multimodal Neural Architecture Search","created":"2020-04-25","cited_by_count":34},{"id":"2203.15516","title":"Rich Feature Construction for the Optimization-Generalization Dilemma","created":"2022-03-24","cited_by_count":34},{"id":"2007.15829","title":"Adversarial Bipartite Graph Learning for Video Domain Adaptation","created":"2020-07-31","cited_by_count":28},{"id":"2106.15792","title":"Learning Bounds for Open-Set Learning","created":"2021-06-30","cited_by_count":27},{"id":"2403.18274","title":"DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment","created":"2024-03-27","cited_by_count":26},{"id":"2402.17888","title":"ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection","created":"2024-02-27","cited_by_count":22},{"id":"2203.01386","title":"Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification","created":"2022-03-02","cited_by_count":21},{"id":"2403.13556","title":"Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments","created":"2024-03-20","cited_by_count":21},{"id":"2404.13153","title":"Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring","created":"2024-04-19","cited_by_count":20},{"id":"2408.11051","title":"FLAME: Learning to Navigate with Multimodal LLM in Urban Environments","created":"2024-08-20","cited_by_count":19},{"id":"2205.11166","title":"Prompt Tuning for Discriminative Pre-trained Language Models","created":"2022-05-23","cited_by_count":17},{"id":"2401.16634","title":"The Why, When, and How to Use Active Learning in Large-Data-Driven 3D Object Detection for Safe Autonomous Driving: An Empirical Exploration","created":"2024-01-30","cited_by_count":17},{"id":"2206.11655","title":"Optimizing Two-way Partial AUC with an End-to-end Framework","created":"2022-06-23","cited_by_count":15},{"id":"2305.02519","title":"ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos","created":"2023-05-04","cited_by_count":15},{"id":"2307.07942","title":"KECOR: Kernel Coding Rate Maximization for Active 3D Object Detection","created":"2023-07-16","cited_by_count":13},{"id":"2402.04286","title":"Progress and Opportunities of Foundation Models in Bioinformatics","created":"2024-02-06","cited_by_count":13},{"id":"2403.11789","title":"EMIE-MAP: Large-Scale Road Surface Reconstruction Based on Explicit Mesh and Implicit Encoding","created":"2024-03-18","cited_by_count":13},{"id":"2410.04844","title":"PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing","created":"2024-10-07","cited_by_count":10},{"id":"2306.01598","title":"Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning","created":"2023-06-02","cited_by_count":9},{"id":"2304.13976","title":"Moderately Distributional Exploration for Domain Generalization","created":"2023-04-27","cited_by_count":8},{"id":"2412.01857","title":"Planning from Imagination: Episodic Simulation and Episodic Memory for Vision-and-Language Navigation","created":"2024-11-30","cited_by_count":8},{"id":"1808.07209","title":"Coarse-to-Fine Annotation Enrichment for Semantic Segmentation Learning","created":"2018-08-22","cited_by_count":7},{"id":"2402.14430","title":"Robust Training of Federated Models with Extremely Label Deficiency","created":"2024-02-22","cited_by_count":7},{"id":"2502.07216","title":"SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer","created":"2025-02-11","cited_by_count":7},{"id":"2407.14644","title":"Human-Interpretable Adversarial Prompt Attack on Large Language Models with Situational Context","created":"2024-07-19","cited_by_count":6},{"id":"2007.09676","title":"Learning Error-Driven Curriculum for Crowd Counting","created":"2020-07-19","cited_by_count":5},{"id":"2403.05660","title":"Decoupling Degradations with Recurrent Network for Video Restoration in Under-Display Camera","created":"2024-03-08","cited_by_count":5},{"id":"2202.08495","title":"Predict the Rover Mobility over Soft Terrain using Articulated Wheeled Bevameter","created":"2022-02-17","cited_by_count":4},{"id":"2209.01994","title":"Federated Zero-Shot Learning for Visual Recognition","created":"2022-09-05","cited_by_count":4},{"id":"2408.14135","title":"Foodfusion: A Novel Approach for Food Image Composition via Diffusion Models","created":"2024-08-26","cited_by_count":4},{"id":"2405.11154","title":"Revisiting the Robust Generalization of Adversarial Prompt Tuning","created":"2024-05-18","cited_by_count":3},{"id":"2406.04478","title":"PromptFix: Few-shot Backdoor Removal via Adversarial Prompt Tuning","created":"2024-06-06","cited_by_count":2},{"id":"2203.12814","title":"Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering","created":"2022-03-24","cited_by_count":1}],"next_cursor":null}