PhaseWin: An Efficient Search Algorithm for Faithful Visual Attribution
About
Visual attribution is a fundamental tool for interpreting modern vision and vision-language models, particularly when their decisions must be inspected, diagnosed, or audited. Its goal is to explain how a model's decision depends on local regions of the visual input, typically by assigning an importance ordering over candidate image regions. Given an image partitioned into $n$ regions, faithful attribution can be cast as an ordered subset-search problem, in which progressively inserting the selected regions should recover the target model response as early as possible. Exhaustive search over region subsets incurs exponential cost, while the widely used greedy search still requires a quadratic number of model evaluations, because every selection step rescores all remaining candidates. We propose PhaseWin, an efficient subset-search algorithm for faithful visual attribution. PhaseWin reorganizes greedy region selection into a phased window-search procedure: rather than re-evaluating the full candidate set at every step, it alternates between global candidate screening, adaptive pruning, and localized window refinement, while preserving the essential region-ranking behavior of greedy search. We analyze PhaseWin under monotone evidence-accumulation conditions and show that, under feature-level structural assumptions, it attains controllable linear evaluation complexity together with near-greedy faithfulness guarantees. Extensive experiments on image classification, object detection, visual grounding, and image captioning show that, among all compared attribution methods, PhaseWin reaches high faithfulness with the fewest forward passes, empirically realizing the predicted reduction from $O(n^2)$ to $O(n)$. The code is available at https://github.com/Qihuai27/phasewin-va.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Attributing Multimodal Foundation Model Errors | ImageNet misclassified samples (val) | Avg Highest Confidence (0-50%)81.05 | 30 | |
| Classification attribution | ImageNet (misclassified samples) | Ins. Score63.11 | 29 | |
| Classification attribution | ImageNet correct samples | Insertion Score0.8037 | 19 | |
| Hallucination Attribution | POPE | Ins Score92.53 | 16 | |
| Hallucination Attribution | RePOPE | Insertion Score77.83 | 16 | |
| Classification attribution | ImageNet correctly classified samples (val) | Insertion Score0.799 | 15 | |
| Caption token attribution | COCO | Insertion Score63.51 | 12 | |
| Object Detection | MS-COCO (val) | Insertion76.15 | 12 | |
| Image Classification Attribution | ImageNet Cause | Insertion Score66.04 | 12 | |
| Image Classification Attribution | ImageNet (Repair) | Insertion (Ins)44.82 | 12 |