{"total":19,"rows":[{"id":"2308.13320","title":"Fine-tuning can cripple your foundation model; preserving features may be the solution","created":"2023-08-25","cited_by_count":96,"area":null},{"id":"2305.06061","title":"Visual Tuning","created":"2023-05-10","cited_by_count":34,"area":null},{"id":"2401.01736","title":"Few-shot Adaptation of Multi-modal Foundation Models: A Survey","created":"2024-01-03","cited_by_count":28,"area":null},{"id":"2308.12509","title":"Parameter-Efficient Transfer Learning for Remote Sensing Image-Text Retrieval","created":"2023-08-24","cited_by_count":24,"area":null},{"id":"2501.18592","title":"Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models","created":"2025-01-30","cited_by_count":23,"area":null},{"id":"2403.12702","title":"Learning Cross-view Visual Geo-localization without Ground Truth","created":"2024-03-19","cited_by_count":18,"area":null},{"id":"2401.04651","title":"Learning to Prompt Segment Anything Models","created":"2024-01-09","cited_by_count":13,"area":null},{"id":"2410.09004","title":"DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection","created":"2024-10-11","cited_by_count":8,"area":null},{"id":"2311.13612","title":"Descriptor and Word Soups: Overcoming the Parameter Efficiency Accuracy Tradeoff for Out-of-Distribution Few-shot Learning","created":"2023-11-21","cited_by_count":6,"area":null},{"id":"2411.19346","title":"CLIP meets DINO for Tuning Zero-Shot Classifier using Unlabeled Image Collections","created":"2024-11-28","cited_by_count":5,"area":null},{"id":"2306.04715","title":"UniBoost: Unsupervised Unimodal Pre-training for Boosting Zero-shot Vision-Language Tasks","created":"2023-06-07","cited_by_count":4,"area":null},{"id":"2401.07669","title":"SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels","created":"2024-01-15","cited_by_count":4,"area":null},{"id":"2408.14348","title":"Deep learning-based ecological analysis of camera trap images is impacted by training data quality and quantity","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2411.15099","title":"Context-Aware Multimodal Pretraining","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2409.11338","title":"CLIP Adaptation by Intra-modal Overlap Reduction","created":"2024-09-17","cited_by_count":2,"area":null},{"id":"2601.00993","title":"WildIng: A Wildlife Image Invariant Representation Model for Geographical Domain Shift","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2603.04341","title":"Hold-One-Shot-Out (HOSO) for Validation-Free Few-Shot CLIP Adapters","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2407.05647","title":"Learning to Adapt Category Consistent Meta-Feature of CLIP for Few-Shot Classification","created":"2024-07-08","cited_by_count":0,"area":null},{"id":"2511.08036","title":"WEDepth: Efficient Adaptation of World Knowledge for Monocular Depth Estimation","created":"2025-11-11","cited_by_count":0,"area":null}],"next_cursor":null}