Papers with Code 아카이브
Unsupervised Semantic Segmentation with Language-image Pre-training
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 12
- 보존된 평가 기록
- 94
A segmentation task which does not utilise any human-level supervision for semantic segmentation except for a backbone which is initialised with features pre-trained with image-level labels.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training
ITACLIP: Boosting Training-Free Semantic Segmentation with Image, Text, and Architectural Enhancements
CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training
Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs
Perceptual Grouping in Contrastive Vision-Language Models
ReCo: Retrieve and Co-segment for Zero-shot Transfer
GroupViT: Semantic Segmentation Emerges from Text Supervision
Extract Free Dense Labels from CLIP
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.