COMPUTER VISION

Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning

April 11, 2023

Abstract

We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP’s con- trastive loss, intending to train an alignment between the patch tokens of the vision encoder and the CLS token of the text encoder. With such an alignment, a model can identify regions of an image corresponding to a given text input, and therefore transfer seamlessly to the task of open vocabulary semantic segmentation without requiring any segmentation annotations during training. Using pre-trained CLIP en- coders with PACL, we are able to set the state-of-the-art on the task of open vocabulary zero-shot segmentation on 4 different segmentation benchmarks: Pascal VOC, Pascal Context, COCO Stuff and ADE20K. Furthermore, we show that PACL is also applicable to image-level predictions and when used with a CLIP backbone, provides a general im- provement in zero-shot classification accuracy compared to CLIP, across a suite of 12 image classification datasets.

Download the Paper

AUTHORS

Written by

Jishnu Mukhoti

Tsung-Yu Lin

Omid Poursaeed

Rui (VisionX) Wang

Ashish Shah

Philip Torr

Ser-Nam Lim

Publisher

CVPR

Research Topics

Computer Vision

Related Publications

September 30, 2023

INTEGRITY

COMPUTER VISION

The Stable Signature: Rooting Watermarks in Latent Diffusion Models

Pierre Fernandez, Guillaume Couairon, Hervé Jegou, Matthijs Douze, Teddy Furon

September 30, 2023

September 29, 2023

COMPUTER VISION

Among Us: Adversarially Robust Collaborative Perception by Consensus

Yiming Li, Qi Fang, Jiamu Bai, Siheng Chen, Felix Xu, Chen Feng

September 29, 2023

September 27, 2023

COMPUTER VISION

Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack

Xiaoliang Dai, Ji Hou, Kevin Chih-Yao Ma, Sam Tsai, Jialiang Wang, Rui Wang, Peizhao Zhang, Simon Vandenhende, Xiaofang Wang, Abhimanyu Dubey, Matthew Yu, Abhishek Kadian, Filip Radenovic, Dhruv Mahajan, Kunpeng Li, Yue (R) Zhao, Vladan Petrovic, Mitesh Kumar Singh, Simran Motwani, Yiwen Song, Yi Wen, Roshan Sumbaly, Vignesh Ramanathan, Zijian He, Peter Vajda, Devi Parikh

September 27, 2023

September 22, 2023

COMPUTER VISION

CORE MACHINE LEARNING

Common Corruption Robustness of Point Cloud Detectors: Benchmark and Enhancement

Shuangzhi Li, Zhijie Wang, Felix Xu, Qing Guo, Xingyu Li, Lei Ma

September 22, 2023

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.