Papers Unsupervised Semantic Segmentation with Language-image Pre-training
“Unsupervised Semantic Segmentation with Language-image Pre-training” 태그가 달린 논문 14편 · 필터 해제
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+1TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
We identify a critical bias in contemporary CLIP-based models, which we denote as single tag bias. This bias manifests as a disproportionate focus on a singular tag (word) while neglecting other pertinent tags, stemming …
Multi-Label Text ClassificationOpen Vocabulary Semantic SegmentationSemantic SegmentationTAG+1TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data. Existing attempts usually face the problem of coarse alignment, e.g., the vision encoder struggl…
AttributeOpen Vocabulary Semantic SegmentationSemantic SegmentationTAG+1TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training
Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to capture the global features to distinguish dif…
ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONSemantic Segmentation+3Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs
We tackle open-world semantic segmentation, which aims at learning to segment arbitrary visual concepts in images, by using only image-text pairs without dense annotations. Existing open-world segmentation methods have s…
Contrastive LearningOpen Vocabulary Semantic SegmentationSegmentationSemantic Segmentation+2Perceptual Grouping in Contrastive Vision-Language Models
Recent advances in zero-shot image recognition suggest that vision-language models learn generic visual representations with a high degree of semantic information that may be arbitrarily probed with natural language phra…
Object LocalizationRepresentation LearningUnsupervised Semantic SegmentationUnsupervised Semantic Segmentation with Language-image Pre-trainingReCo: Retrieve and Co-segment for Zero-shot Transfer
Semantic segmentation has a broad range of applications, but its real-world impact has been significantly limited by the prohibitive annotation costs necessary to enable deployment. Segmentation methods that forgo superv…
RetrievalSegmentationSemantic SegmentationUnsupervised Semantic Segmentation+1GroupViT: Semantic Segmentation Emerges from Text Supervision
Grouping and recognition are important components of visual scene understanding, e.g., for object detection and semantic segmentation. With end-to-end deep learning systems, grouping of image regions usually happens impl…
Object DetectionScene UnderstandingSemantic SegmentationTransfer Learning+1Extract Free Dense Labels from CLIP
Contrastive Language-Image Pre-training (CLIP) has made a remarkable breakthrough in open-vocabulary zero-shot image recognition. Many recent studies leverage the pre-trained CLIP models for image-level classification an…
Novel ConceptsOpen Vocabulary Panoptic SegmentationSegmentationSemantic Segmentation+3