Find Your Needle: Small Object Image Retrieval Via Multi-object Attention Optimization
2025 · Michael Green, Matan Levy, Issar Tzachor, et al.
Abstract
We address the challenge of Small Object Image Retrieval (SoIR), where the goal is to retrieve images containing a specific small object, in a cluttered scene. The key challenge in this setting is constructing a single image descriptor, for scalable and efficient search, that effectively represents all objects in the image. In this paper, we first analyze the limitations of existing methods on this challenging task and then introduce new benchmarks to support SoIR evaluation. Next, we introduce Multi-object Attention Optimization (MaO), a novel retrieval framework which incorporates a dedicated multi-object pre-training phase. This is followed by a refinement process that leverages attention-based feature extraction with object masks, integrating them into a single unified image descriptor. Our MaO approach significantly outperforms existing retrieval methods and strong baselines, achieving notable improvements in both zero-shot and lightweight multi-object fine-tuning. We hope this wo
Authors
(none)
Tags
Stats
Related papers
- SORCE: Small Object Retrieval In Complex Environments (2025)0.00
- Object-centric Open-vocabulary Image-retrieval With Aggregated Features (2023)0.00
- FOR: Finetuning For Object Level Open Vocabulary Image Retrieval (2024)0.00
- Prompt-guided Attention Head Selection For Focus-oriented Image Retrieval (2025)0.00
- IDMR: Towards Instance-driven Precise Visual Correspondence In Multimodal Retrieval (2025)2.29
- Efficient Object Embedding For Spliced Image Retrieval (2019)8.09
- Tasks Integrated Networks: Joint Detection And Retrieval For Image Search (2020)11.08
- Composed Object Retrieval: Object-level Retrieval Via Composed Expressions (2025)1.91