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.
PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts
SkateboardAI: The Coolest Video Action Recognition for Skateboarding
Zero-Shot Learning by Harnessing Adversarial Samples
MAiVAR-T: Multimodal Audio-image and Video Action Recognizer using Transformers
DDG-Net: Discriminability-Driven Graph Network for Weakly-supervised Temporal Action Localization
From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement
TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion Prediction
Fuzzy Logic Visual Network (FLVN): A neuro-symbolic approach for visual features matching
Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
Learning Snippet-to-Motion Progression for Skeleton-based Human Motion Prediction
Developing and Evaluating Tiny to Medium-Sized Turkish BERT Models
Zshot: An Open-source Framework for Zero-Shot Named Entity Recognition and Relation Extraction
PRIOR: Prototype Representation Joint Learning from Medical Images and Reports
Spatiotemporal Modeling Encounters 3D Medical Image Analysis: Slice-Shift UNet with Multi-View Fusion
Wisdom of Instruction-Tuned Language Model Crowds. Exploring Model Label Variation
Evaluating the Ripple Effects of Knowledge Editing in Language Models
Validation of a Zero-Shot Learning Natural Language Processing Tool for Data Abstraction from Unstructured Healthcare Data
Two-stream Multi-level Dynamic Point Transformer for Two-person Interaction Recognition
Leveraging Knowledge Graphs for Zero-Shot Object-agnostic State Classification
See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Data
AGAR: Attention Graph-RNN for Adaptative Motion Prediction of Point Clouds of Deformable Objects
Human Action Recognition in Still Images Using ConViT
Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP
Fusing Hand and Body Skeletons for Human Action Recognition in Assembly
SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training
Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation
Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer
Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
Improving Zero-Shot Generalization for CLIP with Synthesized Prompts
Interactive Spatiotemporal Token Attention Network for Skeleton-based General Interactive Action Recognition
CoTracker: It is Better to Track Together
Free-Form Composition Networks for Egocentric Action Recognition
Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition
AutoHint: Automatic Prompt Optimization with Hint Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.