Abstract:Composed Image Retrieval (CIR) requires both preserving the visual continuity of the reference image and faithfully executing the semantic variables specified in the modification text, which constitute the core challenge of the task. Existing methods often suffer from Perception Myopia in a single space, or fall into Logic Drift in iterative collaboration due to the perception ceiling of the underlying retriever. To address this issue, we propose a one-stop hierarchical Perception-to-Deliberation Framework (PDF), which, to the best of our knowledge, is the first to introduce experience self-evolution and Test-Time Scaling Laws (TTS) into CIR. Relying on a hierarchical multi-agent architecture, PDF first utilizes an Intent Routing Manager to dynamically dispatch multi-view Worker perception signals based on modification intents to construct a high-recall candidate pool. Subsequently, the Decision Manager combines a Training-free Reasoning Policy Distillation mechanism with a Tournament-style TTS (T-TTS) strategy to achieve self-evolving fine-grained reasoning, yielding the final retrieval results. Experimental results demonstrate that PDF achieves SOTA performance on three benchmark datasets: CIRR, CIRCO, and FashionIQ. This study indicates that experience-driven self-evolution and TTS represent a highly promising and scalable path for achieving zero-shot fine-grained multimedia retrieval. The code will be made publicly available upon acceptance.
| Comments: | 10 pages, 5 figures,4 tables |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2605.22478 [cs.CV] |
| (or arXiv:2605.22478v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.22478 arXiv-issued DOI via DataCite |
From: Xingtian Pei [view email]
[v1]
Thu, 21 May 2026 13:36:38 UTC (5,651 KB)
[v2]
Sat, 23 May 2026 05:02:33 UTC (5,650 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。