Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Vision-Language Models, Zero-Shot Generalization, Test-Time Adaptation, CLIP reward
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We propose to improve the zero-shot generalization capacity of vision-language models on the fly with CLIP as the feedback source.
Abstract: One fascinating aspect of pre-trained vision-language models (VLMs) learning under language supervision is their impressive zero-shot generalization capability.
However, this ability is hindered by distribution shifts between the training and testing data.
Previous test time adaptation (TTA) methods for VLMs in zero-shot classification rely on minimizing the entropy of model outputs, tending to be stuck in incorrect model predictions.
In this work, we propose TTA with feedback to rectify the model output and prevent the model from becoming blindly confident.
Specifically, a CLIP model is adopted as the reward model during TTA and provides feedback for the VLM.
Given a single test sample,
the VLM is forced to maximize the CLIP reward between the input and sampled results from the VLM output distribution.
The proposed \textit{reinforcement learning with CLIP feedback~(RLCF)} framework is highly flexible and universal.
Beyond the classification task, with task-specific sampling strategies and a proper reward baseline choice, RLCF can be easily extended to not only discrimination tasks like retrieval but also generalization tasks like image captioning,
improving the zero-shot generalization capacity of VLMs.
According to the characteristics of these VL tasks, we build different fully TTA pipelines with RLCF to improve the zero-shot generalization ability of various VLMs.
Extensive experiments along with promising
empirical results demonstrate the effectiveness of RLCF.
The code is available at https://github.com/mzhaoshuai/RLCF.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: representation learning for computer vision, audio, language, and other modalities
Submission Number: 4239
Loading