Instance-level image retrieval is the task of searching in a large database for images that match an object in a query image. To address this task, systems usually rely on a retrieval step that uses global image descriptors, and a subsequent step that performs domain-specific refinements or reranking by leveraging operations such as geometric verification based on local features. In this work, we propose Reranking Transformers (RRTs) as a general model to incorporate both local and global features to rerank the matching images in a supervised fashion and thus replace the relatively expensive process of geometric verification. RRTs are lightweight and can be easily parallelized so that reranking a set of top matching results can be performed in a single forward-pass. We perform extensive experiments on the Revisited Oxford and Paris datasets, and the Google Landmarks v2 dataset, showing that RRTs outperform previous reranking approaches while using much fewer local descriptors. Moreover, we demonstrate that, unlike existing approaches, RRTs can be optimized jointly with the feature extractor, which can lead to feature representations tailored to downstream tasks and further accuracy improvements. The code and trained models are publicly available at https://github.com/uvavision/RerankingTransformer.
UniCVR: From Alignment to Reranking for Unified Zero-Shot Composed Visual Retrieval
Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));City University of Hong Kong(香港城市大学);Southern University of Science and Technology(南方科技大学);Pengcheng Laboratory(鹏城实验室)
Towards Efficient and Robust Moment Retrieval System: A Unified Framework for Multi-Granularity Models and Temporal Reranking
University of Information Technology(信息科技大学);Ho Chi Minh University of Technology(胡志明市技术大学);Hanoi University of Science and Technology(河内理工大学);Michigan State University(密歇根州立大学);National Economics University(国民经济大学);Posts and Telecommunications Institute of Technology(邮电技术学院);York University(约克大学)
Dual-Route Top-K Retrieval with 1v1 VLM Reranking for the CoVR-R
Southeast University(东南大学);National University of Singapore(新加坡国立大学);Independent Researcher(独立研究者);Opus AI Research(Opus AI研究);University of Science and Technology of China(中国科学技术大学)
R3G: A Reasoning-Retrieval-Reranking Framework for Vision-Centric Answer Generation
The Shenzhen International Graduate School, Tsinghua University, China(清华大学深圳国际研究生院);State Key Laboratory of Nuclear Power Safety Technology and Equipment, China(核能安全技术与装备国家重点实验室);School of Computer Science and Information Engineering, Hefei University of Technology, China(合肥工业大学计算机科学与信息工程学院)
Heterogeneous Vision-Language Ensemble with Disagreement-Aware Reranking for Text-Based Person Anomaly Retrieval
Hanoi University of Science and Technology(河内科技大学);University of Information Technology, VNU-HCM(胡志明市国家大学信息技术大学);Vietnam National University, Ho Chi Minh City(胡志明市国家大学);VinUniversity;Vietnamese-German University(越南德国大学)
MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence
MoE Key Laboratory of Brain-Machine Intelligence Technology, College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics(脑机智能技术MoE实验室,人工智能学院,南京航空航天大学);Nanjing University(南京大学);The Hong Kong Polytechnic University(香港理工大学)