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.
LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text
Beyond the Visible: Multispectral Vision-Language Learning for Earth Observation
Bayesian Test-Time Adaptation for Vision-Language Models
MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification
MedUnifier: Unifying Vision-and-Language Pre-training on Medical Data with Vision Generation Task using Discrete Visual Representations
Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion
KPL: Training-Free Medical Knowledge Mining of Vision-Language Models
Post-hoc Probabilistic Vision-Language Models
CLIP-PING: Boosting Lightweight Vision-Language Models with Proximus Intrinsic Neighbors Guidance
TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives
TaxaBind: A Unified Embedding Space for Ecological Applications
Retrieval-enriched zero-shot image classification in low-resource domains
Multilingual Vision-Language Pre-training for the Remote Sensing Domain
Altogether: Image Captioning via Re-aligning Alt-text
Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability
Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
CSA: Data-efficient Mapping of Unimodal Features to Multimodal Features
LoGra-Med: Long Context Multi-Graph Alignment for Medical Vision-Language Model
CLIP-MoE: Towards Building Mixture of Experts for CLIP with Diversified Multiplet Upcycling
Anytime Continual Learning for Open Vocabulary Classification
DPA: Dual Prototypes Alignment for Unsupervised Adaptation of Vision-Language Models
Do Vision-Language Foundational models show Robust Visual Perception?
CoAPT: Context Attribute words for Prompt Tuning
Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion
Semantic Compositions Enhance Vision-Language Contrastive Learning
PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration
Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP
WATT: Weight Average Test-Time Adaptation of CLIP
BaFTA: Backprop-Free Test-Time Adaptation For Zero-Shot Vision-Language Models
FusionBench: A Comprehensive Benchmark of Deep Model Fusion
Mind's Eye: Image Recognition by EEG via Multimodal Similarity-Keeping Contrastive Learning
Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships
It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap
What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models
Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.