发表机构
Shanghai Jiao Tong University; Shanghai Innovation Institute; University College London; OPPO（上海交通大学; 上海创新研究院; 伦敦大学学院; OPPO）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
AMBER提出自适应多视图预算化Elo重排序框架，动态分配VLM调用预算，在CIRR、CIRCO和PhotoBench上以更少调用实现更强重排序性能。
AI 中文摘要
视觉-语言模型（VLM）是强大的多模态检索列表式重排序器，但高昂的推理成本限制了其只能评估较小的局部候选视图。现有的多调用策略依赖固定调度，将昂贵的VLM调用浪费在无信息量的候选对和简单查询上。为解决这一问题，我们提出了自适应多视图预算化Elo重排序（AMBER），一种在线、预算化的多视图重排序框架，能够动态优化全局资源分配。AMBER将碎片化的列表式VLM输出视为局部锦标赛，利用连续的Elo更新来维护轻量级的全局排序状态。在此基础上，它在两个层面分配计算资源：动态构建具有高分数歧义的候选视图，以及调度查询以最大化预期信息增益。我们证明了每次Elo更新对应于Bradley-Terry对数似然上的随机梯度上升步骤，并为查询级分配策略提供了子模信息论动机。在CIRR、CIRCO和PhotoBench上的实验表明，在相当的VLM调用预算下，AMBER在比较的多调用VLM重排序方法中取得了最强的整体性能，同时在较低预算设置下也保持有效。我们的代码可在以下网址公开获取：https://this https URL。
英文摘要
Vision-language models (VLMs) are powerful listwise rerankers for multimodal retrieval, but high inference costs restrict them to evaluating small local candidate views. Existing multi-call strategies rely on fixed schedules, wasting expensive VLM calls on uninformative candidate pairs and easy queries. To address this, we propose Adaptive Multi-view Budgeted Elo Reranking (AMBER), an online, budgeted multi-view reranking framework that dynamically optimizes global resource allocation. AMBER treats fragmented listwise VLM outputs as local tournaments, using continuous Elo updates to maintain a lightweight global ranking state. Building on this, it allocates computation at two levels: dynamically constructing candidate views with high score ambiguity, and scheduling queries to maximize expected information gain. We show that each Elo update corresponds to a stochastic gradient ascent step on the Bradley-Terry log-likelihood, and provide a submodular information-theoretic motivation for the query-level allocation strategy. Experiments on CIRR, CIRCO, and PhotoBench demonstrate that AMBER achieves the strongest overall performance among the compared multi-call VLM reranking methods under comparable VLM-call budgets, while remaining effective in lower-budget settings. Our code is publicly available at https://github.com/wnlfc/AMBER.
