Saved in:
Bibliographic Details
Main Authors: Wu, Cheng-En, Lin, Jinhong, Hu, Yu Hen, Morgado, Pedro
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.14607
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915038746378240
author Wu, Cheng-En
Lin, Jinhong
Hu, Yu Hen
Morgado, Pedro
author_facet Wu, Cheng-En
Lin, Jinhong
Hu, Yu Hen
Morgado, Pedro
contents Contrastive image-text pre-trained models such as CLIP have shown remarkable adaptability to downstream tasks. However, they face challenges due to the high computational requirements of the Vision Transformer (ViT) backbone. Current strategies to boost ViT efficiency focus on pruning patch tokens but fall short in addressing the multimodal nature of CLIP and identifying the optimal subset of tokens for maximum performance. To address this, we propose greedy search methods to establish a "Golden Ranking" and introduce a lightweight predictor specifically trained to approximate this Ranking. To compensate for any performance degradation resulting from token pruning, we incorporate learnable visual tokens that aid in restoring and potentially enhancing the model's performance. Our work presents a comprehensive and systematic investigation of pruning tokens within the ViT backbone of CLIP models. Through our framework, we successfully reduced 40% of patch tokens in CLIP's ViT while only suffering a minimal average accuracy loss of 0.3 across seven datasets. Our study lays the groundwork for building more computationally efficient multimodal models without sacrificing their performance, addressing a key challenge in the application of advanced vision-language models.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14607
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Patch Ranking: Efficient CLIP by Learning to Rank Local Patches
Wu, Cheng-En
Lin, Jinhong
Hu, Yu Hen
Morgado, Pedro
Computer Vision and Pattern Recognition
Machine Learning
Contrastive image-text pre-trained models such as CLIP have shown remarkable adaptability to downstream tasks. However, they face challenges due to the high computational requirements of the Vision Transformer (ViT) backbone. Current strategies to boost ViT efficiency focus on pruning patch tokens but fall short in addressing the multimodal nature of CLIP and identifying the optimal subset of tokens for maximum performance. To address this, we propose greedy search methods to establish a "Golden Ranking" and introduce a lightweight predictor specifically trained to approximate this Ranking. To compensate for any performance degradation resulting from token pruning, we incorporate learnable visual tokens that aid in restoring and potentially enhancing the model's performance. Our work presents a comprehensive and systematic investigation of pruning tokens within the ViT backbone of CLIP models. Through our framework, we successfully reduced 40% of patch tokens in CLIP's ViT while only suffering a minimal average accuracy loss of 0.3 across seven datasets. Our study lays the groundwork for building more computationally efficient multimodal models without sacrificing their performance, addressing a key challenge in the application of advanced vision-language models.
title Patch Ranking: Efficient CLIP by Learning to Rank Local Patches
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2409.14607