Tyck till om SwePub Sök här!
WFRF:(Khan Wasim)
Sökning: WFRF:(Khan Wasim) > Self-regulating Pro...
Self-regulating Prompts: Foundational Model Adaptation without Forgetting
-
- Khattak, Muhammad Uzair (författare)
- Mohamed Bin Zayed Univ AI, U Arab Emirates
-
- Wasim, Syed Talal (författare)
- Mohamed Bin Zayed Univ AI, U Arab Emirates
-
- Naseer, Muzammal (författare)
- Mohamed Bin Zayed Univ AI, U Arab Emirates
- visa fler...
- visa färre...
- (creator_code:org_t)
- IEEE COMPUTER SOC, 2023
- 2023
- Engelska.
- Ingår i: 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023). - : IEEE COMPUTER SOC. - 9798350307184 - 9798350307191 ; , s. 15144-15154
- Konferensbidrag (refereegranskat)
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Annan data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Other Computer and Information Science (hsv//eng)
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
- 2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023) (Sök värdpublikationen i LIBRIS)
Till lärosätets databas
Hitta mer i SwePub
- Av författaren/redakt...
- Khattak, Muhamma ...
- Wasim, Syed Tala ...
- Naseer, Muzammal
- Khan, Salman
- Yang, Ming-Hsuan
- Khan, Fahad
- Om ämnet
-
- NATURVETENSKAP
- NATURVETENSKAP
- och Data och informa ...
- och Annan data och i ...
- Artiklar i publikationen
- 2023 IEEE/CVF IN ...
- Av lärosätet
- Linköpings universitet
Sök utanför SwePub
- Sök vidare i:
- Google Book Search
- Google Scholar
Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.
- Copyright © LIBRIS - Nationella bibliotekssystem
- LIBRIS.kb.se
