Papers with Code 아카이브
Zero-Shot Image Classification
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 3
- 보존된 평가 기록
- 3
Zero-shot image classification is a technique in computer vision where a model can classify images into categories that were not present during training. This is achieved by leveraging semantic information about the categories, such as textual descriptions or relationships between classes.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
MoDE: CLIP Data Experts via Clustering
A Progressive Framework of Vision-language Knowledge Distillation and Alignment for Multilingual Scene
Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning
Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations
Bridge the Modality and Capability Gaps in Vision-Language Model Selection
Can We Talk Models Into Seeing the World Differently?
PromptKD: Unsupervised Prompt Distillation for Vision-Language Models
Exploring Low-Resource Medical Image Classification with Weakly Supervised Prompt Learning
Image-Caption Encoding for Improving Zero-Shot Generalization
Segment Any Change
Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment
CLAMP: Contrastive LAnguage Model Prompt-tuning
LightCLIP: Learning Multi-Level Interaction for Lightweight Vision-Language Models
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language Models
Efficient Model-Agnostic Multi-Group Equivariant Networks
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
Noise-Tolerant Few-Shot Unsupervised Adapter for Vision-Language Models
GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training
PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
Distilling Large Vision-Language Model with Out-of-Distribution Generalizability
Continual Learning in Open-vocabulary Classification with Complementary Memory Systems
RemoteCLIP: A Vision Language Foundation Model for Remote Sensing
Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding
Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations
Semantically-Prompted Language Models Improve Visual Descriptions
Learning from Children: Improving Image-Caption Pretraining via Curriculum
CamDiff: Camouflage Image Augmentation via Diffusion Model
Text-to-Image Diffusion Models are Zero-Shot Classifiers
Structure Pretraining and Prompt Tuning for Knowledge Graph Transfer
CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
Language-Driven Anchors for Zero-Shot Adversarial Robustness
Vision-Language Models Performing Zero-Shot Tasks Exhibit Gender-based Disparities
DiRaC-I: Identifying Diverse and Rare Training Classes for Zero-Shot Learning
When are Lemons Purple? The Concept Association Bias of Vision-Language Models
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.