Adaptive Diversity Cache：面向长尾人-物交互检测的自适应测试时记忆分配

View PDF HTML (experimental)

Abstract:Long-tailed human-object interaction (HOI) detection remains challenging because rare interactions are sparsely represented in training data. Although test observations provide additional visual evidence, existing cache-based methods typically assign uniform memory capacity across classes, limiting their ability to capture informative features of underrepresented interactions. To address this issue, we propose Adaptive Diversity Cache (ADC), a training-free, plug-and-play framework that adaptively constructs test-time caches through frequency-aware capacity allocation and confidence-diversity joint sample selection. Specifically, Frequency-Aware Cache Adaptation assigns larger capacities to underrepresented interactions using frequency-dependent priorities and a weighted logarithmic allocation objective, and fills remaining slots with selected augmented views. Confidence-Diversity Joint Cache Selection further combines prediction confidence with local feature diversity to retain informative cache entries. Cache retrieval then refines the predictions of the frozen detector. Experiments on HICO-DET and V-COCO across three base detectors demonstrate consistent improvements. On HICO-DET, ADC improves mean average precision (mAP) for rare interactions by 4.02--8.57 percentage points, while also improving performance on non-rare interactions. Online adaptation further achieves gains of 2.87--7.36 percentage points on rare interactions. These results demonstrate that adaptive test-time memory effectively complements existing HOI detectors and improves long-tailed detection performance.

Submission history

From: Yuqiu Jiang [view email]
[v1] Mon, 24 Nov 2025 06:30:08 UTC (3,228 KB)
[v2] Tue, 10 Mar 2026 13:53:03 UTC (2,666 KB)
[v3] Thu, 5 Nov 2026 08:22:36 UTC (2,183 KB)