Summary of Stamp: Outlier-aware Test-time Adaptation with Stable Memory Replay, by Yongcan Yu et al.
STAMP: Outlier-Aware Test-Time Adaptation with Stable Memory Replay
by Yongcan Yu, Lijun Sheng, Ran He, Jian Liang
First submitted to arxiv on: 22 Jul 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computer Vision and Pattern Recognition (cs.CV)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed STAble Memory rePlay (STAMP) approach aims to address test-time adaptation by optimizing a stable memory bank and performing both sample recognition and outlier rejection during open-world inference. This is achieved through dynamic updating of the memory bank using low-entropy, label-consistent samples in a class-balanced manner, as well as self-weighted entropy minimization. The results demonstrate that STAMP outperforms existing TTA methods in terms of recognition and outlier detection performance. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper proposes a new approach to test-time adaptation called STAble Memory rePlay (STAMP). It helps machines learn from data they’ve never seen before by recognizing known classes and rejecting unknown ones. The method uses a special memory bank that gets updated with low-entropy, label-consistent samples in a balanced way. This makes it better at identifying both familiar and unfamiliar patterns. The results show that STAMP is more effective than other methods in recognizing known classes and detecting unknown ones. |
Keywords
» Artificial intelligence » Inference » Outlier detection
