通过动态缓存类别特征，让模型更准确识别未知数据。
DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectors
- 为每类已知数据建立独立缓存，收集高熵样本
- 测试时用缓存特征校准预测，降低对未知样本的过度自信
- 无需训练，可无缝接入多种检测方法，效果显著
Out-of-distribution（OOD）检测仍是深度神经网络的核心挑战，尤其因模型在测试时对未见的未知样本产生过度自信预测。我们发现关键现象：被预测为同一类别的未知样本之间，视觉上比真实已知分布样本更相似。基于此类别特异性观察，提出DCAC（Dynamic Class-Aware Cache），一种无需训练、仅在测试时使用的校准模块。该模块为每个已知类别维护独立缓存，收集高熵样本，并通过轻量级两层结构，利用缓存的视觉特征和预测概率，校准输入样本的原始输出。该模块可无缝集成于多种现有OOD检测方法，涵盖单模态与视觉-语言模型，计算开销极小。在多个主流OOD基准上的大量实验表明，DCAC显著提升现有方法性能，在ImageNet OOD基准上与ASH-S结合时，将FPR95降低6.55%。
原文摘要 · Abstract (English)
Out-of-distribution (OOD) detection remains a fundamental challenge for deep neural networks, particularly due to overconfident predictions on unseen OOD samples during testing. We reveal a key insight: OOD samples predicted as the same class, or given high probabilities for it, are visually more similar to each other than to the true in-distribution (ID) samples. Motivated by this class-specific observation, we propose DCAC (Dynamic Class-Aware Cache), a training-free, test-time calibration module that maintains separate caches for each ID class to collect high-entropy samples and calibrate the raw predictions of input samples. DCAC leverages cached visual features and predicted probabilities through a lightweight two-layer module to mitigate overconfident predictions on OOD samples. This module can be seamlessly integrated with various existing OOD detection methods across both unimodal and vision-language models while introducing minimal computational overhead. Extensive experiments on multiple OOD benchmarks demonstrate that DCAC significantly enhances existing methods, achieving substantial improvements, i.e., reducing FPR95 by 6.55% when integrated with ASH-S on ImageNet OOD benchmark.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。