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

Philip Torr

Tsung-Yu Lin

Ashish Shah

Omid Poursaeed

Rui (VisionX) Wang

Ser-Nam Lim

Publisher

CVPR

Research Topics

Computer Vision

Related Publications

April 14, 2026

COMPUTER VISION

ML APPLICATIONS

TransText: Transparency Aware Image-to-Video Typography Animation

Zijian Zhou, Bohao Tang, Pengfei Liu, Fei Zhang, Frost Xu, Hang Li (BizAI), Semih Gunel, Sen He, Soubhik Sanyal, Tao Xiang, Viktar Atliha, Zhe Wang

April 14, 2026

April 09, 2026

HUMAN & MACHINE INTELLIGENCE

COMPUTER VISION

Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning

Lei Zhang, Junjiao Tian, Kunpeng Li, Jialiang Wang, Weifeng Chen, Yuxiao Bao, Julian McAuley, Manling Li, Zecheng He, Felix Xu, Markos Georgopoulos, Zhipeng Fan

April 09, 2026

February 27, 2026

HUMAN & MACHINE INTELLIGENCE

RESEARCH

Unified Vision–Language Modeling via Concept Space Alignment

Yifu Qiu, Holger Schwenk, Paul-Ambroise Duquenne

February 27, 2026

February 11, 2026

RESEARCH

COMPUTER VISION

UniT: Unified Multimodal Chain-of-Thought Test-time Scaling

Leon Liangyu Chen, Haoyu Ma, Ziqi Huang, Xiaoliang Dai, Jialiang Wang, Zecheng He, Jianwei Yang, Chunyuan Li, Serena Yeung-Levy, Animesh Sinha, Chu Wang, Felix Juefei-Xu, Junzhe Sun, Zhipeng Fan

February 11, 2026

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.