OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910633374515200 |
|---|---|
| author | Li, Siyuan Wang, Zedong Liu, Zicheng Tian, Juanxi Wu, Di Tan, Cheng Jin, Weiyang Li, Stan Z. |
| author_facet | Li, Siyuan Wang, Zedong Liu, Zicheng Tian, Juanxi Wu, Di Tan, Cheng Jin, Weiyang Li, Stan Z. |
| contents | Mixup augmentation has emerged as a widely used technique for improving the generalization ability of deep neural networks (DNNs). However, the lack of standardized implementations and benchmarks has impeded recent progress, resulting in poor reproducibility, unfair comparisons, and conflicting insights. In this paper, we introduce OpenMixup, the first mixup augmentation codebase, and benchmark for visual representation learning. Specifically, we train 18 representative mixup baselines from scratch and rigorously evaluate them across 11 image datasets of varying scales and granularity, ranging from fine-grained scenarios to complex non-iconic scenes. We also open-source our modular codebase, including a collection of popular vision backbones, optimization strategies, and analysis toolkits, which not only supports the benchmarking but enables broader mixup applications beyond classification, such as self-supervised learning and regression tasks. Through experiments and empirical analysis, we gain observations and insights on mixup performance-efficiency trade-offs, generalization, and optimization behaviors, and thereby identify preferred choices for different needs. To the best of our knowledge, OpenMixup has facilitated several recent studies. We believe this work can further advance reproducible mixup augmentation research and thereby lay a solid ground for future progress in the community. The source code and user documents are available at \url{https://github.com/Westlake-AI/openmixup}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2209_04851 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning Li, Siyuan Wang, Zedong Liu, Zicheng Tian, Juanxi Wu, Di Tan, Cheng Jin, Weiyang Li, Stan Z. Computer Vision and Pattern Recognition Mixup augmentation has emerged as a widely used technique for improving the generalization ability of deep neural networks (DNNs). However, the lack of standardized implementations and benchmarks has impeded recent progress, resulting in poor reproducibility, unfair comparisons, and conflicting insights. In this paper, we introduce OpenMixup, the first mixup augmentation codebase, and benchmark for visual representation learning. Specifically, we train 18 representative mixup baselines from scratch and rigorously evaluate them across 11 image datasets of varying scales and granularity, ranging from fine-grained scenarios to complex non-iconic scenes. We also open-source our modular codebase, including a collection of popular vision backbones, optimization strategies, and analysis toolkits, which not only supports the benchmarking but enables broader mixup applications beyond classification, such as self-supervised learning and regression tasks. Through experiments and empirical analysis, we gain observations and insights on mixup performance-efficiency trade-offs, generalization, and optimization behaviors, and thereby identify preferred choices for different needs. To the best of our knowledge, OpenMixup has facilitated several recent studies. We believe this work can further advance reproducible mixup augmentation research and thereby lay a solid ground for future progress in the community. The source code and user documents are available at \url{https://github.com/Westlake-AI/openmixup}. |
| title | OpenMixup: Open Mixup Toolbox and Benchmark for Visual Representation Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2209.04851 |