Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913585925455872 |
|---|---|
| author | Tran, Minh-Tuan Le, Trung Le, Xuan-May Cai, Jianfei Harandi, Mehrtash Phung, Dinh |
| author_facet | Tran, Minh-Tuan Le, Trung Le, Xuan-May Cai, Jianfei Harandi, Mehrtash Phung, Dinh |
| contents | Data-Free Knowledge Distillation (DFKD) is an advanced technique that enables knowledge transfer from a teacher model to a student model without relying on original training data. While DFKD methods have achieved success on smaller datasets like CIFAR10 and CIFAR100, they encounter challenges on larger, high-resolution datasets such as ImageNet. A primary issue with previous approaches is their generation of synthetic images at high resolutions (e.g., $224 \times 224$) without leveraging information from real images, often resulting in noisy images that lack essential class-specific features in large datasets. Additionally, the computational cost of generating the extensive data needed for effective knowledge transfer can be prohibitive. In this paper, we introduce MUlti-reSolution data-freE (MUSE) to address these limitations. MUSE generates images at lower resolutions while using Class Activation Maps (CAMs) to ensure that the generated images retain critical, class-specific features. To further enhance model diversity, we propose multi-resolution generation and embedding diversity techniques that strengthen latent space representations, leading to significant performance improvements. Experimental results demonstrate that MUSE achieves state-of-the-art performance across both small- and large-scale datasets, with notable performance gains of up to two digits in nearly all ImageNet and subset experiments. Code is available at https://github.com/tmtuan1307/muse. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_17046 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation Tran, Minh-Tuan Le, Trung Le, Xuan-May Cai, Jianfei Harandi, Mehrtash Phung, Dinh Computer Vision and Pattern Recognition Data-Free Knowledge Distillation (DFKD) is an advanced technique that enables knowledge transfer from a teacher model to a student model without relying on original training data. While DFKD methods have achieved success on smaller datasets like CIFAR10 and CIFAR100, they encounter challenges on larger, high-resolution datasets such as ImageNet. A primary issue with previous approaches is their generation of synthetic images at high resolutions (e.g., $224 \times 224$) without leveraging information from real images, often resulting in noisy images that lack essential class-specific features in large datasets. Additionally, the computational cost of generating the extensive data needed for effective knowledge transfer can be prohibitive. In this paper, we introduce MUlti-reSolution data-freE (MUSE) to address these limitations. MUSE generates images at lower resolutions while using Class Activation Maps (CAMs) to ensure that the generated images retain critical, class-specific features. To further enhance model diversity, we propose multi-resolution generation and embedding diversity techniques that strengthen latent space representations, leading to significant performance improvements. Experimental results demonstrate that MUSE achieves state-of-the-art performance across both small- and large-scale datasets, with notable performance gains of up to two digits in nearly all ImageNet and subset experiments. Code is available at https://github.com/tmtuan1307/muse. |
| title | Large-Scale Data-Free Knowledge Distillation for ImageNet via Multi-Resolution Data Generation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2411.17046 |