Tyck till om SwePub Sök
här!
Search: WFRF:(Khan Wasim) >
Self-regulating Pro...
Self-regulating Prompts: Foundational Model Adaptation without Forgetting
-
- Khattak, Muhammad Uzair (author)
- Mohamed Bin Zayed Univ AI, U Arab Emirates
-
- Wasim, Syed Talal (author)
- Mohamed Bin Zayed Univ AI, U Arab Emirates
-
- Naseer, Muzammal (author)
- Mohamed Bin Zayed Univ AI, U Arab Emirates
-
show more...
-
- Khan, Salman (author)
- Mohamed Bin Zayed Univ AI, U Arab Emirates; Australian Natl Univ, Australia
-
- Yang, Ming-Hsuan (author)
- Univ Calif, CA USA; Google Res, CA USA
-
- Khan, Fahad (author)
- Linköpings universitet,Datorseende,Tekniska fakulteten,Mohamed Bin Zayed Univ AI, U Arab Emirates
-
show less...
-
(creator_code:org_t)
- IEEE COMPUTER SOC, 2023
- 2023
- English.
-
In: 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023). - : IEEE COMPUTER SOC. - 9798350307184 - 9798350307191 ; , s. 15144-15154
- Related links:
-
https://urn.kb.se/re...
-
show more...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Prompt learning has emerged as an efficient alternative for fine-tuning foundational models, such as CLIP, for various downstream tasks. Conventionally trained using the task-specific objective, i.e., cross-entropy loss, prompts tend to overfit downstream data distributions and find it challenging to capture task-agnostic general features from the frozen CLIP. This leads to the loss of the model's original generalization capability. To address this issue, our work introduces a self-regularization framework for prompting called PromptSRC (Prompting with Self-regulating Constraints). PromptSRC guides the prompts to optimize for both task-specific and task-agnostic general representations using a three-pronged approach by: (a) regulating prompted representations via mutual agreement maximization with the frozen model, (b) regulating with selfensemble of prompts over the training trajectory to encode their complementary strengths, and (c) regulating with textual diversity to mitigate sample diversity imbalance with the visual branch. To the best of our knowledge, this is the first regularization framework for prompt learning that avoids overfitting by jointly attending to pre-trained model features, the training trajectory during prompting, and the textual diversity. PromptSRC explicitly steers the prompts to learn a representation space that maximizes performance on downstream tasks without compromising CLIP generalization. We perform extensive experiments on 4 benchmarks where PromptSRC overall performs favorably well compared to the existing methods. Our code and pre-trained models are publicly available at: https://github.com/muzairkhattak/PromptSRC.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Annan data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Other Computer and Information Science (hsv//eng)
Publication and Content Type
- ref (subject category)
- kon (subject category)
Find in a library
To the university's database