DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting

TL;DR

DenseCLIP introduces a novel framework that leverages pre-trained CLIP knowledge for dense prediction tasks by converting image-text matching into pixel-text matching and using contextual prompts, achieving superior results across multiple vision tasks.

Contribution

The paper presents a model-agnostic approach that adapts CLIP for dense prediction by pixel-text matching and contextual prompting, extending CLIP's capabilities beyond classification.

Findings

Superior performance on semantic segmentation

Effective on object detection and instance segmentation

Compatible with various pre-trained backbones

Abstract

Recent progress has shown that large-scale pre-training using contrastive image-text pairs can be a promising alternative for high-quality visual representation learning from natural language supervision. Benefiting from a broader source of supervision, this new paradigm exhibits impressive transferability to downstream classification tasks and datasets. However, the problem of transferring the knowledge learned from image-text pairs to more complex dense prediction tasks has barely been visited. In this work, we present a new framework for dense prediction by implicitly and explicitly leveraging the pre-trained knowledge from CLIP. Specifically, we convert the original image-text matching problem in CLIP to a pixel-text matching problem and use the pixel-text score maps to guide the learning of dense prediction models. By further using the contextual information from the image to prompt the language model, we are able to facilitate our model to better exploit the pre-trained knowledge. Our method is model-agnostic, which can be applied to arbitrary dense prediction systems and various pre-trained visual backbones including both CLIP models and ImageNet pre-trained models. Extensive experiments demonstrate the superior performance of our methods on semantic segmentation, object detection, and instance segmentation tasks. Code is available at https://github.com/raoyongming/DenseCLIP