# DCAC: Dynamic Class-Aware Cache Creates Stronger Out-of-Distribution Detectors

arXiv: https://arxiv.org/abs/2601.12468 · HTML: https://mlsanity.com/paper/2601.12468/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 18 Jan 2026.

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [ReAct: Out-of-distribution Detection With Rectified Activations](https://mlsanity.com/paper/2111.12797/) (2021)
- [Gradient Starvation: A Learning Proclivity in Neural Networks](https://mlsanity.com/paper/2011.09468/) (2020)
- [Delving into Out-of-Distribution Detection with Vision-Language Representations](https://mlsanity.com/paper/2211.13445/) (2022)
- [In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation](https://mlsanity.com/paper/2306.00826/) (2023)
- [LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning](https://mlsanity.com/paper/2306.01293/) (2023)
- [OODD: Test-time Out-of-Distribution Detection with Dynamic Dictionary](https://mlsanity.com/paper/2503.10468/) (2025)
- [Knowledge Guided Disambiguation for Large-Scale Scene Classification with Multi-Resolution CNNs](https://mlsanity.com/paper/1610.01119/) (2016)
- [FodFoM: Fake Outlier Data by Foundation Models Creates Stronger Visual Out-of-Distribution Detector](https://mlsanity.com/paper/2412.05293/) (2024)
- [End-to-end Convolutional Network for Saliency Prediction](https://mlsanity.com/paper/1507.01422/) (2015)
- [TULiP: Test-time Uncertainty Estimation via Linearization and Weight Perturbation](https://mlsanity.com/paper/2505.16923/) (2025)

## Built on by (most cited first, 3 of 3)

- [TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Models](https://mlsanity.com/paper/2604.15756/) (2026)
- [DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection](https://mlsanity.com/paper/2604.23729/) (2026)
- [CHILD: Human-in-the-Loop OOD Detection for Safe Clinical Deployment](https://mlsanity.com/paper/2609.07188/) (2026)

## Abstract (arXiv)

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.