Zero-Shot Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 7
- 평가표
- 33
- 보존된 평가 기록
- 84
Zero-shot learning (ZSL) is a model's ability to detect classes never seen during training. The condition is that the classes are not known during supervised learning.
Earlier work in zero-shot learning use attributes in a two-step approach to infer unknown classes. In the computer vision context, more recent advances learn mappings from image feature space to semantic space. Other approaches learn non-linear multimodal embeddings. In the modern NLP context, language models can be evaluated on downstream tasks without fine tuning.
Benchmark datasets for zero-shot learning include aPY, AwA, and CUB, among others.
( Image credit: Prototypical Networks for Few shot Learning in PyTorch )
Further readings:
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations
AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving
BadEdit: Backdooring large language models by model editing
HierCode: A Lightweight Hierarchical Codebook for Zero-shot Chinese Text Recognition
RAR: Retrieving And Ranking Augmented MLLMs for Visual Recognition
Editing Massive Concepts in Text-to-Image Diffusion Models
Entity6K: A Large Open-Domain Evaluation Dataset for Real-World Entity Recognition
Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning
CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation
UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All
Audio-Visual Compound Expression Recognition Method based on Late Modality Fusion and Rule-based Decision
MEDBind: Unifying Language and Multimodal Medical Data Embeddings
Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models
SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction
Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters
Meta-Prompting for Automating Zero-shot Visual Recognition with LLMs
Leveraging Large Language Models to Extract Information on Substance Use Disorder Severity from Clinical Notes: A Zero-shot Learning Approach
Large Language Models Powered Context-aware Motion Prediction in Autonomous Driving
Boosting Semi-Supervised Temporal Action Localization by Learning from Non-Target Classes
A Lie Group Approach to Riemannian Batch Normalization
Pioneering SE(2)-Equivariant Trajectory Planning for Automated Driving
MambaMOT: State-Space Model as Motion Predictor for Multi-Object Tracking
Skeleton-Based Human Action Recognition with Noisy Labels
CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner
CoLeCLIP: Open-Domain Continual Learning via Joint Task Prompt and Vocabulary Learning
Leveraging Foundation Model Automatic Data Augmentation Strategies and Skeletal Points for Hands Action Recognition in Industrial Assembly Lines
Select and Distill: Selective Dual-Teacher Knowledge Transfer for Continual Learning on Vision-Language Models
Sentinel-Guided Zero-Shot Learning: A Collaborative Paradigm without Real Data Exposure
OpenGraph: Open-Vocabulary Hierarchical 3D Graph Representation in Large-Scale Outdoor Environments
SkateFormer: Skeletal-Temporal Transformer for Human Action Recognition
Video Mamba Suite: State Space Model as a Versatile Alternative for Video Understanding
On the Utility of 3D Hand Poses for Action Recognition
MolBind: Multimodal Alignment of Language, Molecules, and Proteins
Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification
Segmentation of Knee Bones for Osteoarthritis Assessment: A Comparative Analysis of Supervised, Few-Shot, and Zero-Shot Learning Approaches
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.