# Test-Time Discovery via Hashing Memory

arXiv: https://arxiv.org/abs/2503.10699 · HTML: https://mlsanity.com/paper/2503.10699/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [DualPrompt: Complementary Prompting for Rehearsal-free Continual Learning](https://mlsanity.com/paper/2204.04799/) (2022)
- [Contrastive Test-Time Adaptation](https://mlsanity.com/paper/2204.10377/) (2022)
- [Learning to Discover Novel Visual Categories via Deep Transfer Clustering](https://mlsanity.com/paper/1908.09884/) (2019)
- [Test-Time Training with Masked Autoencoders](https://mlsanity.com/paper/2209.07522/) (2022)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Parameter-free Online Test-time Adaptation](https://mlsanity.com/paper/2201.05718/) (2022)
- [Robust Test-Time Adaptation in Dynamic Scenarios](https://mlsanity.com/paper/2303.13899/) (2023)
- [Reducing Network Agnostophobia](https://mlsanity.com/paper/1811.04110/) (2018)
- [Automatically Discovering and Learning New Visual Categories with Ranking Statistics](https://mlsanity.com/paper/2002.05714/) (2020)
- [Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation](https://mlsanity.com/paper/2107.03358/) (2021)
- [PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery](https://mlsanity.com/paper/2212.05590/) (2022)
- [Exploring Example Influence in Continual Learning](https://mlsanity.com/paper/2209.12241/) (2022)
- [TTTFlow: Unsupervised Test-Time Training with Normalizing Flow](https://mlsanity.com/paper/2210.11389/) (2022)
- [Understanding the Feature Norm for Out-of-Distribution Detection](https://mlsanity.com/paper/2310.05316/) (2023)
- [A Strong Baseline for Generalized Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2211.14126/) (2022)
- [Revisiting Realistic Test-Time Training: Sequential Inference and Adaptation by Anchored Clustering Regularized Self-Training](https://mlsanity.com/paper/2303.10856/) (2023)
- [Effective Prompt Pool Learning for Continual Category Discovery](https://mlsanity.com/paper/2407.19001/) (2024)
- [Variational Continual Test-Time Adaptation](https://mlsanity.com/paper/2402.08182/) (2024)
- [Controllable Continual Test-Time Adaptation](https://mlsanity.com/paper/2405.14602/) (2024)
- [Parameter-Selective Continual Test-Time Adaptation](https://mlsanity.com/paper/2407.02253/) (2024)
- [Conformal Uncertainty Indicator for Continual Test-Time Adaptation](https://mlsanity.com/paper/2502.02998/) (2025)

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

- [Test-Time Generalized Category Discovery](https://mlsanity.com/paper/2609.33937/) (2026)
- [Energy Ring: Stabilizing Feature Energy for Reliable Test-Time Discovery](https://mlsanity.com/paper/2610.14525/) (2026)
- [Relational Semantic Grounding for Test-Time Discovery](https://mlsanity.com/paper/2610.14721/) (2026)

## Abstract (arXiv)

We introduce Test-Time Discovery (TTD) as a novel task that addresses class shifts during testing, requiring models to simultaneously identify emerging categories while preserving previously learned ones. A key challenge in TTD is distinguishing newly discovered classes from those already identified. To address this, we propose a training-free, hash-based memory mechanism that enhances class discovery through fine-grained comparisons with past test samples. Leveraging the characteristics of unknown classes, our approach introduces hash representation based on feature scale and directions, utilizing Locality-Sensitive Hashing (LSH) for efficient grouping of similar samples. This enables test samples to be easily and quickly compared with relevant past instances. Furthermore, we design a collaborative classification strategy, combining a prototype classifier for known classes with an LSH-based classifier for novel ones. To enhance reliability, we incorporate a self-correction mechanism that refines memory labels through hash-based neighbor retrieval, ensuring more stable and accurate class assignments. Experimental results demonstrate that our method achieves good discovery of novel categories while maintaining performance on known classes, establishing a new paradigm in model testing. Our code is available at https://github.com/fanlyu/ttd.