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.
ModelPS: An Interactive and Collaborative Platform for Editing Pre-trained Models at Scale
Zero-Shot Recommender Systems
Human Motion Prediction Using Manifold-Aware Wasserstein GAN
Multi-Person Extreme Motion Prediction
VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living
REGINA - Reasoning Graph Convolutional Networks in Human Action Recognition
Multiple-Input Multiple-Output Fusion Network For Generalized Zero-Shot Learning
Semantic Diversity Learning for Zero-Shot Multi-label Classification
Action Shuffling for Weakly Supervised Temporal Localization
Zero-Shot Personalized Speech Enhancement through Speaker-Informed Model Selection
Test-Time Adaptation Toward Personalized Speech Enhancement: Zero-Shot Learning with Knowledge Distillation
Continuous representations of intents for dialogue systems
Weakly Supervised Action Selection Learning in Video
Learning Skeletal Articulations with Neural Blend Shapes
Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition
One Model to Rule them All: Towards Zero-Shot Learning for Databases
Learning Graph Embeddings for Open World Compositional Zero-Shot Learning
Action in Mind: A Neural Network Approach to Action Recognition and Segmentation
Action Unit Memory Network for Weakly Supervised Temporal Action Localization
Relevance Detection in Cataract Surgery Videos by Spatio-Temporal Action Localization
Revisiting Skeleton-based Action Recognition
Three-stream network for enriched Action Recognition
Dynamic VAEs with Generative Replay for Continual Zero-shot Learning
Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos
Low Pass Filter for Anti-aliasing in Temporal Action Localization
3D Convolutional Neural Networks for Ultrasound-Based Silent Speech Interfaces
A Framework for Unsupervised Classificiation and Data Mining of Tweets about Cyber Vulnerabilities
Attribute-Modulated Generative Meta Learning for Zero-Shot Classification
Hierarchical growing grid networks for skeleton based action recognition
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text
Maneuver-based Anchor Trajectory Hypotheses at Roundabouts
Revisiting Document Representations for Large-Scale Zero-Shot Learning
Skimming and Scanning for Untrimmed Video Action Recognition
Imaginative Walks: Generative Random Walk Deviation Loss for Improved Unseen Learning Representation
CrossATNet - A Novel Cross-Attention Based Framework for Sketch-Based Image Retrieval
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.