PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer
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_ | 1866929410251161600 |
|---|---|
| author | Feng, Qian Zhao, Hanbin Zhang, Chao Dong, Jiahua Ding, Henghui Jiang, Yu-Gang Qian, Hui |
| author_facet | Feng, Qian Zhao, Hanbin Zhang, Chao Dong, Jiahua Ding, Henghui Jiang, Yu-Gang Qian, Hui |
| contents | Incremental Learning (IL) aims to learn deep models on sequential tasks continually, where each new task includes a batch of new classes and deep models have no access to task-ID information at the inference time. Recent vast pre-trained models (PTMs) have achieved outstanding performance by prompt technique in practical IL without the old samples (rehearsal-free) and with a memory constraint (memory-constrained): Prompt-extending and Prompt-fixed methods. However, prompt-extending methods need a large memory buffer to maintain an ever-expanding prompt pool and meet an extra challenging prompt selection problem. Prompt-fixed methods only learn a single set of prompts on one of the incremental tasks and can not handle all the incremental tasks effectively. To achieve a good balance between the memory cost and the performance on all the tasks, we propose a Parameter-Efficient Cross-Task Prompt (PECTP) framework with Prompt Retention Module (PRM) and classifier Head Retention Module (HRM). To make the final learned prompts effective on all incremental tasks, PRM constrains the evolution of cross-task prompts' parameters from Outer Prompt Granularity and Inner Prompt Granularity. Besides, we employ HRM to inherit old knowledge in the previously learned classifier heads to facilitate the cross-task prompts' generalization ability. Extensive experiments show the effectiveness of our method. The source codes will be available at \url{https://github.com/RAIAN08/PECTP}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_03813 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer Feng, Qian Zhao, Hanbin Zhang, Chao Dong, Jiahua Ding, Henghui Jiang, Yu-Gang Qian, Hui Computer Vision and Pattern Recognition Incremental Learning (IL) aims to learn deep models on sequential tasks continually, where each new task includes a batch of new classes and deep models have no access to task-ID information at the inference time. Recent vast pre-trained models (PTMs) have achieved outstanding performance by prompt technique in practical IL without the old samples (rehearsal-free) and with a memory constraint (memory-constrained): Prompt-extending and Prompt-fixed methods. However, prompt-extending methods need a large memory buffer to maintain an ever-expanding prompt pool and meet an extra challenging prompt selection problem. Prompt-fixed methods only learn a single set of prompts on one of the incremental tasks and can not handle all the incremental tasks effectively. To achieve a good balance between the memory cost and the performance on all the tasks, we propose a Parameter-Efficient Cross-Task Prompt (PECTP) framework with Prompt Retention Module (PRM) and classifier Head Retention Module (HRM). To make the final learned prompts effective on all incremental tasks, PRM constrains the evolution of cross-task prompts' parameters from Outer Prompt Granularity and Inner Prompt Granularity. Besides, we employ HRM to inherit old knowledge in the previously learned classifier heads to facilitate the cross-task prompts' generalization ability. Extensive experiments show the effectiveness of our method. The source codes will be available at \url{https://github.com/RAIAN08/PECTP}. |
| title | PECTP: Parameter-Efficient Cross-Task Prompts for Incremental Vision Transformer |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.03813 |