CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement

Mohammadreza Salehi, Mehrdad Farajtabar, Maxwell Horton, Fartash Faghri, Hadi Pouransari, Raviteja Vemulapalli, Oncel Tuzel, Ali Farhadi, Mohammad Rastegari, Sachin Mehta

Keywords: Contrastive Learning, CLIP, Distillation, Dense prediction, 3D Understanding, Task-specific experts

TL;DR: We improve the utility of CLIP representations for tasks that require pixel-level and 3D understanding via pseudo-labeling a large-scale uncurated dataset with task-specific vision experts and training CLIP on them

Abstract: Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. While CLIP is scalable, promptable, and robust to distribution shifts on image classification tasks, it lacks object localization capabilities. This paper studies the following question: Can we augment CLIP training with task-specific vision models from model zoos to improve its visual representations? Towards this end, we leverage open-source task-specific vision models to generate pseudo-labels for an uncurated web-scale image-text dataset. Subsequently, we train CLIP models on these pseudo-labels in addition to the contrastive training on image and text pairs. This simple setup shows substantial improvements of up to 16.3\% across different vision tasks, including segmentation, detection, depth estimation, and surface normal estimation. Importantly, these enhancements are achieved without compromising CLIP's existing capabilities, including its proficiency in promptable zero-shot classification.

Track: Extended Abstract Track

Submission Number: 47