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.
Deep Zero-Shot Learning for Scene Sketch
Unified Generator-Classifier for Efficient Zero-Shot Learning
Zero-Shot Audio Classification Based on Class Label Embeddings
Spatio-Temporal Action Localization in a Weakly Supervised Setting
Learning Character-Agnostic Motion for Motion Retargeting in 2D
Large-scale weakly-supervised pre-training for video action recognition
Egocentric Hand Track and Object-based Human Action Recognition
Human Action Recognition with Deep Temporal Pyramids
3D BAT: A Semi-Automatic, Web-based 3D Annotation Toolbox for Full-Surround, Multi-Modal Data Streams
Curvature: A signature for Action Recognition in Video Sequences
Cross-Modal Message Passing for Two-stream Fusion
Memory-Augmented Temporal Dynamic Learning for Action Recognition
Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition
DynamoNet: Dynamic Action and Motion Network
Large Scale Holistic Video Understanding
A Large-scale Varying-view RGB-D Action Dataset for Arbitrary-view Human Action Recognition
Context-Aware Zero-Shot Learning for Object Recognition
Sequential modeling of Sessions using Recurrent Neural Networks for Skip Prediction
HAUAR: Home Automation Using Action Recognition
Learning Feature-to-Feature Translator by Alternating Back-Propagation for Generative Zero-Shot Learning
Cubic LSTMs for Video Prediction
EV-Action: Electromyography-Vision Multi-Modal Action Dataset
Simple yet efficient real-time pose-based action recognition
Context-Aware Zero-Shot Recognition
Temporal Unet: Sample Level Human Action Recognition using WiFi
DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition
Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition
Human Motion Prediction via Pattern Completion in Latent Representation Space
Decoupling Localization and Classification in Single Shot Temporal Action Detection
Semantically Aligned Bias Reducing Zero Shot Learning
Weakly Supervised Gaussian Networks for Action Detection
REPAIR: Removing Representation Bias by Dataset Resampling
Audio-Visual Model Distillation Using Acoustic Images
SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning
Multi-View Region Adaptive Multi-temporal DMM and RGB Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.