{"ID":6138858,"CreatedAt":"2026-07-09T01:07:32.349475501Z","UpdatedAt":"2026-07-10T18:46:06.623866342Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.06726","arxiv_id":"2607.06726","title":"A Good Initialization is All You Need for Faithful Visual Attribution","abstract":"Faithful visual attribution identifies which image regions support a model prediction. Search-based perturbation methods lead the insertion--deletion faithfulness frontier by masking regions and measuring score changes, but they usually output a complete ordering of all regions. Many applications, especially MLLM attribution and repair, only need a compact top-\\(k\\) evidence mask. We study this mask-first attribution problem. An exactly \\(k\\)-region mask is combinatorial: useful evidence can depend on interactions among fine regions. Coarse grouping can stabilize early search but aggregates redundant content, whereas one-step scoring can miss high-value combinations. We introduce two forward-only methods. \\textsc{CoPAIR} uses a PhaseWin--Greedy gap diagnosis to construct coarse singleton/pair candidates that warm-start full-ordering search. \\textsc{TRACE} directly searches fixed-cardinality fine-region masks with cross-entropy sampling, elite retention, and distribution updates, with a finite-budget recovery analysis. The resulting evidence set can be returned as a compact attribution mask or used to initialize Greedy or PhaseWin when a complete ranking is required. Across ImageNet classification with CLIP ViT-L/14, CLIP RN101, and ResNet-101, our initialized search methods establish a new state-of-the-art frontier for faithful full-ordering attribution under inclusive forward-call accounting. On POPE and RePOPE with Qwen2.5-VL-3B-Instruct and LLaVA-v1.5-7B, \\textsc{TRACE}+Greedy gives the strongest search-based MLLM attribution results. Direct \\textsc{TRACE} masks further achieve single-point RePOPE repair rates of \\(94.44\\%\\) and \\(96.00\\%\\), showing that compact evidence masks can be actionable attribution outputs, not merely prefixes of full rankings.","short_abstract":"Faithful visual attribution identifies which image regions support a model prediction. Search-based perturbation methods lead the insertion--deletion faithfulness frontier by masking regions and measuring score changes, but they usually output a complete ordering of all regions. Many applications, especially MLLM attri...","url_abs":"https://arxiv.org/abs/2607.06726","url_pdf":"https://arxiv.org/pdf/2607.06726v1","authors":"[\"Zihan Gu\",\"Jiayu Wang\",\"Hua Zhang\",\"Yue Hu\"]","published":"2026-07-07T18:47:45Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\"]","has_code":false}