GPS: Distilling Compact Memories via Grid-based Patch Sampling for Efficient Online Class-Incremental Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909579899568128 |
|---|---|
| author | Ma, Mingchuan Zhou, Yuhao Lv, Jindi Tian, Yuxin Si, Dan Li, Shujian Ye, Qing Lv, Jiancheng |
| author_facet | Ma, Mingchuan Zhou, Yuhao Lv, Jindi Tian, Yuxin Si, Dan Li, Shujian Ye, Qing Lv, Jiancheng |
| contents | Online class-incremental learning aims to enable models to continuously adapt to new classes with limited access to past data, while mitigating catastrophic forgetting. Replay-based methods address this by maintaining a small memory buffer of previous samples, achieving competitive performance. For effective replay under constrained storage, recent approaches leverage distilled data to enhance the informativeness of memory. However, such approaches often involve significant computational overhead due to the use of bi-level optimization. Motivated by these limitations, we introduce Grid-based Patch Sampling (GPS), a lightweight and effective strategy for distilling informative memory samples without relying on a trainable model. GPS generates informative samples by sampling a subset of pixels from the original image, yielding compact low-resolution representations that preserve both semantic content and structural information. During replay, these representations are reassembled to support training and evaluation. Experiments on extensive benchmarks demonstrate that GRS can be seamlessly integrated into existing replay frameworks, leading to 3%-4% improvements in average end accuracy under memory-constrained settings, with limited computational overhead. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_10409 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GPS: Distilling Compact Memories via Grid-based Patch Sampling for Efficient Online Class-Incremental Learning Ma, Mingchuan Zhou, Yuhao Lv, Jindi Tian, Yuxin Si, Dan Li, Shujian Ye, Qing Lv, Jiancheng Computer Vision and Pattern Recognition Online class-incremental learning aims to enable models to continuously adapt to new classes with limited access to past data, while mitigating catastrophic forgetting. Replay-based methods address this by maintaining a small memory buffer of previous samples, achieving competitive performance. For effective replay under constrained storage, recent approaches leverage distilled data to enhance the informativeness of memory. However, such approaches often involve significant computational overhead due to the use of bi-level optimization. Motivated by these limitations, we introduce Grid-based Patch Sampling (GPS), a lightweight and effective strategy for distilling informative memory samples without relying on a trainable model. GPS generates informative samples by sampling a subset of pixels from the original image, yielding compact low-resolution representations that preserve both semantic content and structural information. During replay, these representations are reassembled to support training and evaluation. Experiments on extensive benchmarks demonstrate that GRS can be seamlessly integrated into existing replay frameworks, leading to 3%-4% improvements in average end accuracy under memory-constrained settings, with limited computational overhead. |
| title | GPS: Distilling Compact Memories via Grid-based Patch Sampling for Efficient Online Class-Incremental Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.10409 |