{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1812.01754","title":"Moment Matching for Multi-Source Domain Adaptation","created":"2018-12-04","cited_by_count":1331},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"1706.07522","title":"Deep Hashing Network for Unsupervised Domain Adaptation","created":"2017-06-22","cited_by_count":1188},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1710.03077","title":"Deeper, Broader and Artier Domain Generalization","created":"2017-10-09","cited_by_count":986},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"1807.04975","title":"Recognition in Terra Incognita","created":"2018-07-13","cited_by_count":658},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2007.02454","title":"Self-Challenging Improves Cross-Domain Generalization","created":"2020-07-05","cited_by_count":426},{"id":"2303.04803","title":"Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Models","created":"2023-03-08","cited_by_count":375},{"id":"2003.13216","title":"Learning to Learn Single Domain Generalization","created":"2020-03-30","cited_by_count":296},{"id":"2007.03304","title":"Learning to Generate Novel Domains for Domain Generalization","created":"2020-07-07","cited_by_count":296},{"id":"2105.11120","title":"A Fourier-based Framework for Domain Generalization","created":"2021-05-24","cited_by_count":290},{"id":"1804.10745","title":"Generalizing Across Domains via Cross-Gradient Training","created":"2018-04-28","cited_by_count":268},{"id":"2104.09937","title":"Gradient Matching for Domain Generalization","created":"2021-04-20","cited_by_count":258},{"id":"2006.07500","title":"Domain Generalization using Causal Matching","created":"2020-06-12","cited_by_count":225},{"id":"2108.11726","title":"Learning to Diversify for Single Domain Generalization","created":"2021-08-26","cited_by_count":170},{"id":"2306.05427","title":"Grounded Text-to-Image Synthesis with Attention Refocusing","created":"2023-06-08","cited_by_count":164},{"id":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151},{"id":"2007.13003","title":"Robust and Generalizable Visual Representation Learning via Random Convolutions","created":"2020-07-25","cited_by_count":142},{"id":"2209.15162","title":"Linearly Mapping from Image to Text Space","created":"2022-09-30","cited_by_count":142},{"id":"2203.14237","title":"Causality Inspired Representation Learning for Domain Generalization","created":"2022-03-27","cited_by_count":138},{"id":"2203.10789","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","created":"2022-03-21","cited_by_count":133},{"id":"2303.10353","title":"Sharpness-Aware Gradient Matching for Domain Generalization","created":"2023-03-18","cited_by_count":102},{"id":"2311.02262","title":"Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs","created":"2023-11-03","cited_by_count":91},{"id":"2204.08040","title":"NICO++: Towards Better Benchmarking for Domain Generalization","created":"2022-04-17","cited_by_count":86},{"id":"2307.15199","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","created":"2023-07-27","cited_by_count":59},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55},{"id":"2402.04087","title":"A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation","created":"2024-02-06","cited_by_count":53},{"id":"2208.08340","title":"Dual Modality Prompt Tuning for Vision-Language Pre-Trained Model","created":"2022-08-17","cited_by_count":52},{"id":"2402.07410","title":"A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)","created":"2024-02-12","cited_by_count":44},{"id":"1904.12543","title":"Adversarial Invariant Feature Learning with Accuracy Constraint for Domain Generalization","created":"2019-04-29","cited_by_count":43},{"id":"2304.03709","title":"Meta-causal Learning for Single Domain Generalization","created":"2023-04-07","cited_by_count":43},{"id":"2305.18010","title":"Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models","created":"2023-05-29","cited_by_count":38},{"id":"2302.09251","title":"StyLIP: Multi-Scale Style-Conditioned Prompt Learning for CLIP-based Domain Generalization","created":"2023-02-18","cited_by_count":36},{"id":"2210.04206","title":"Attention Diversification for Domain Generalization","created":"2022-10-09","cited_by_count":29},{"id":"2407.01400","title":"GalLoP: Learning Global and Local Prompts for Vision-Language Models","created":"2024-07-01","cited_by_count":29},{"id":"2404.19286","title":"Soft Prompt Generation for Domain Generalization","created":"2024-04-30","cited_by_count":24},{"id":"2209.14926","title":"Domain-Unified Prompt Representations for Source-Free Domain Generalization","created":"2022-09-29","cited_by_count":21},{"id":"2403.05053","title":"PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering","created":"2024-03-08","cited_by_count":20},{"id":"2305.15542","title":"TOAST: Transfer Learning via Attention Steering","created":"2023-05-24","cited_by_count":15},{"id":"2402.00672","title":"Exploring Homogeneous and Heterogeneous Consistent Label Associations for Unsupervised Visible-Infrared Person ReID","created":"2024-02-01","cited_by_count":13},{"id":"2403.07292","title":"Continual All-in-One Adverse Weather Removal with Knowledge Replay on a Unified Network Structure","created":"2024-03-12","cited_by_count":13},{"id":"2410.02247","title":"Theoretical Insights into Fine-Tuning Attention Mechanism: Generalization and Optimization","created":"2024-10-03","cited_by_count":9},{"id":"2305.13046","title":"POEM: Polarization of Embeddings for Domain-Invariant Representations","created":"2023-05-22","cited_by_count":8},{"id":"2401.15657","title":"Data-Free Generalized Zero-Shot Learning","created":"2024-01-28","cited_by_count":8},{"id":"2401.17186","title":"Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning","created":"2024-01-30","cited_by_count":8},{"id":"2405.15961","title":"Grounding Stylistic Domain Generalization with Quantitative Domain Shift Measures and Synthetic Scene Images","created":"2024-05-24","cited_by_count":6},{"id":"2402.08532","title":"Captions Are Worth a Thousand Words: Enhancing Product Retrieval with Pretrained Image-to-Text Models","created":"2024-02-13","cited_by_count":2}],"next_cursor":null}