Class Agnostic Instance-level Descriptor for Visual Instance Search
Qi-Ying Sun, Wan-Lei Zhao, Hui-Ying Xie, Yi-Bo Miao, Chong-Wah Ngo

TL;DR
This paper introduces a class-agnostic, hierarchical, instance-level feature descriptor derived from self-supervised ViT features, enabling effective image and instance search across known and unknown categories.
Contribution
It proposes a novel hierarchical region discovery method that produces uniform features for various instance granularities, unifying multiple retrieval tasks.
Findings
Effective on both known and unknown object categories
Improves performance in single-instance and multi-instance search
Enhances image retrieval accuracy
Abstract
Despite the great success of the deep features in content-based image retrieval, the visual instance search remains challenging due to the lack of effective instance-level feature representation. Supervised or weakly supervised object detection methods are not the appropriate solutions due to their poor performance on the unknown object categories. In this paper, based on the feature set output from self-supervised ViT, the instance-level region discovery is modeled as detecting the compact feature subsets in a hierarchical fashion. The hierarchical decomposition results in a hierarchy of instance regions. On the one hand, this kind of hierarchical decomposition well addresses the problem of object embedding and occlusions, which are widely observed in real scenarios. On the other hand, the non-leaf nodes and leaf nodes on the hierarchy correspond to the instance regions in different…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsImage Retrieval and Classification Techniques · Advanced Image and Video Retrieval Techniques · Multimodal Machine Learning Applications
Methods+ ( 1 ) ⟷ 888 ⟷ ( 829 ) ⟷ 0881||How do I resolve a dispute on Expedia? · Sparse Evolutionary Training
