홈 › Papers

Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning

2022-12-09 · CVPR 2023 1 · Jishnu Mukhoti, Tsung-Yu Lin, Omid Poursaeed, Rui Wang, Ashish Shah, Philip H. S. Torr, Ser-Nam Lim

We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive 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 encoders 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 improvement in zero-shot classification accuracy compared to CLIP, across a suite of 12 image classification datasets.

📄 PDF Abstract BibTeX arXiv:2212.04994

Code (1)

paulcouairon/diffcut pytorch

Tasks

Contrastive Learning image-classification Image Classification Open Vocabulary Semantic Segmentation Open-Vocabulary Semantic Segmentation Segmentation Semantic Segmentationzero-shot-classificationZero-Shot Learning Zero Shot Segmentation

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Contrastive Learning 설명 없음

Looking Beyond the Window: Global-Local Aligned CLIP for Training-free Open-Vocabulary Semantic Segmentation

2026-03-24 · ByeongCheol Lee, Hyun Seok Seong, Sangeek Hyun, Gilhan Park 외 arxiv

A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-resolution images. However, this approac…

Semantic Segmentation

ConInfer: Context-Aware Inference for Training-Free Open-Vocabulary Remote Sensing Segmentation

2026-03-31 · Wenyang Chen, Zhanxuan Hu, Yaping Zhang, Hailong Ning 외 arxiv

Training-free open-vocabulary remote sensing segmentation (OVRSS), empowered by vision-language models, has emerged as a promising paradigm for achieving category-agnostic semantic understanding in remote sensing imagery…

Semantic Segmentation

T-REN: Learning Text-Aligned Region Tokens Improves Dense Vision-Language Alignment and Scalability

2026-04-20 · Savya Khosla, Sethuraman T, Aryan Chadha, Alex Schwing 외 arxiv

Despite recent progress, vision-language encoders struggle with two core limitations: (1) weak alignment between language and dense vision features, which hurts tasks like open-vocabulary semantic segmentation; and (2) h…

Semantic Segmentation Object Localization Image Retrieval Scene Parsing

CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation

2024-11-15 · Dengke Zhang, Fagui Liu, Quan Tang

Open-vocabulary semantic segmentation aims to assign semantic labels to each pixel without relying on a predefined set of categories. Contrastive Language-Image Pre-training (CLIP) demonstrates outstanding zero-shot clas…

Open Vocabulary Semantic Segmentation Open-Vocabulary Semantic Segmentation Segmentation Semantic Segmentation+3

SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation

2022-11-27 · Huaishao Luo, Junwei Bao, Youzheng Wu, Xiaodong He 외

Recently, the contrastive language-image pre-training, e.g., CLIP, has demonstrated promising results on various downstream tasks. The pre-trained model can capture enriched visual concepts for images by learning from a …

Open Vocabulary Semantic Segmentation Open-Vocabulary Semantic Segmentation Segmentation Semantic Segmentation