Papers with Code 아카이브
Multi-label zero-shot learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 3
- 보존된 평가 기록
- 19
The goal of multi-label classification task is to predict a set of labels in an image. As an extension of zero-shot learning (ZSL), multi-label zero-shot learning (ML-ZSL) is developed to identify multiple seen and unseen labels in an image.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation
Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-Label Medical Image Classification
Label Propagation for Zero-shot Classification with Vision-Language Models
Query-Based Knowledge Sharing for Open-Vocabulary Multi-Label Classification
GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learning
Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features
Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer
Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention
ML-Decoder: Scalable and Versatile Classification Head
Discriminative Region-based Multi-Label Zero-Shot Learning
Contrastive Language-Image Pre-training for the Italian Language
Semantic Diversity Learning for Zero-Shot Multi-label Classification
Generative Multi-Label Zero-Shot Learning
Zero-shot Learning for Audio-based Music Classification and Tagging
Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection
Multi-Label Zero-Shot Learning with Structured Knowledge Graphs
Multi-Label Zero-Shot Human Action Recognition via Joint Latent Ranking Embedding
Multi-Label Zero-Shot Learning via Concept Embedding
Fast Zero-Shot Image Tagging
Label-Embedding for Image Classification
Transductive Multi-label Zero-shot Learning
Transductive Multi-class and Multi-label Zero-shot Learning
Zero-Shot Learning by Convex Combination of Semantic Embeddings
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.