Unsupervised Semantic Segmentation with Language-image Pre-training
12개 벤치마크 · 논문 14편 · 이 태스크의 논문 보기 →
Benchmarks
ADE20K
COCO-Object
COCO-Stuff-171
Cityscapes val
PASCAL Context-59
PASCAL VOC
PascalVOC-20
COCO-Stuff-27
PASCAL Context-60
KITTI-STEP
PASCAL VOC 2007
Most implemented
GroupViT: Semantic Segmentation Emerges from Text Supervision
Perceptual Grouping in Contrastive Vision-Language Models
ReCo: Retrieve and Co-segment for Zero-shot Transfer
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
Papers
TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models
Image-text models excel at image-level tasks but struggle with detailed visual understanding. While these models provide strong visual-language alignment, segmentation models like SAM2 offer precise spatial boundaries fo…
Referring ExpressionReferring Expression ComprehensionSemantic SegmentationUnsupervised Semantic Segmentation with Language-image Pre-trainingCOSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
Vision-Language Models (VLMs) trained with contrastive loss have achieved significant advancements in various vision and language tasks. However, the global nature of the contrastive loss makes VLMs focus predominantly o…
Self-Supervised LearningSemantic SegmentationUnsupervised Semantic Segmentation with Language-image Pre-trainingZero-Shot Cross-Modal Retrieval+1ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements
Recent advances in foundational Vision Language Models (VLMs) have reshaped the evaluation paradigm in computer vision tasks. These foundational models, especially CLIP, have accelerated research in open-vocabulary compu…
Open Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSegmentationSemantic Segmentation+1CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation
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 SegmentationOpen-Vocabulary Semantic SegmentationSegmentationSemantic Segmentation+3Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
While Contrastive Language-Image Pre-training (CLIP) has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatial-invariant semant…
SegmentationSemantic SegmentationUnsupervised Semantic Segmentation with Language-image Pre-trainingProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation
Open-vocabulary semantic segmentation requires models to effectively integrate visual representations with open-vocabulary semantic labels. While Contrastive Language-Image Pre-training (CLIP) models shine in recognizing…
Open Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSegmentationSemantic Segmentation+1