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.
Modality Distillation with Multiple Stream Networks for Action Recognition
GILE: A Generalized Input-Label Embedding for Text Classification
Two Stream Self-Supervised Learning for Action Recognition
One-Shot Unsupervised Cross Domain Translation
Nearly Zero-Shot Learning for Semantic Decoding in Spoken Dialogue Systems
MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
Massively Parallel Video Networks
Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction
BSN: Boundary Sensitive Network for Temporal Action Proposal Generation
Probabilistic AND-OR Attribute Grouping for Zero-Shot Learning
Action4D: Real-time Action Recognition in the Crowd and Clutter
Leolani: a reference machine with a theory of mind for social communication
Deep Mixture of Experts via Shallow Embedding
Neural Network-Based Equations for Predicting PGA and PGV in Texas, Oklahoma, and Kansas
Squeeze-and-Excitation on Spatial and Temporal Deep Feature Space for Action Recognition
A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition
Rethinking Knowledge Graph Propagation for Zero-Shot Learning
Pose-Based Two-Stream Relational Networks for Action Recognition in Videos
DEEPEYE: A Compact and Accurate Video Comprehension at Terminal Devices Compressed with Quantization and Tensorization
Stacked Semantic-Guided Attention Model for Fine-Grained Zero-Shot Learning
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
Progressive Ensemble Networks for Zero-Shot Recognition
Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognition
Fast Retinomorphic Event Stream for Video Recognition and Reinforcement Learning
Multi-Modal Trajectory Prediction of Surrounding Vehicles with Maneuver based LSTMs
Learning Rich Features for Image Manipulation Detection
Towards an Unequivocal Representation of Actions
Visual Attribute-augmented Three-dimensional Convolutional Neural Network for Enhanced Human Action Recognition
Low-Latency Human Action Recognition with Weighted Multi-Region Convolutional Neural Network
Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
Long-Term Human Motion Prediction by Modeling Motion Context and Enhancing Motion Dynamic
Relational Network for Skeleton-Based Action Recognition
Learning Optical Flow via Dilated Networks and Occlusion Reasoning
Object Activity Scene Description, Construction and Recognition
Sketch-a-Classifier: Sketch-based Photo Classifier Generation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.