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.
Train, Diagnose and Fix: Interpretable Approach for Fine-grained Action Recognition
Zero-shot Learning via Shared-Reconstruction-Graph Pursuit
Action Recognition with Coarse-to-Fine Deep Feature Integration and Asynchronous Fusion
Excitation Backprop for RNNs
Action-Attending Graphic Neural Network
Multi-Label Zero-Shot Learning with Structured Knowledge Graphs
Skepxels: Spatio-temporal Image Representation of Human Skeleton Joints for Action Recognition
Learning to Compare: Relation Network for Few-Shot Learning
Zero-Shot Learning via Category-Specific Visual-Semantic Mapping
Attend and Interact: Higher-Order Object Interactions for Video Understanding
Zero-Shot Learning via Class-Conditioned Deep Generative Models
Knowledge transfer for surgical activity prediction
End-to-end Video-level Representation Learning for Action Recognition
Egocentric Hand Detection Via Dynamic Region Growing
Predicting Scene Parsing and Motion Dynamics in the Future
Attentional Pooling for Action Recognition
Radical analysis network for zero-shot learning in printed Chinese character recognition
Graph Attention Networks
Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
3D CNNs on Distance Matrices for Human Action Recognition
Adaptive RNN Tree for Large-Scale Human Action Recognition
A Generative Restricted Boltzmann Machine Based Method for High-Dimensional Motion Data Modeling
Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data
Learning to Recognize Actions from Limited Training Examples Using a Recurrent Spiking Neural Model
Recent Advances in Zero-shot Recognition
Real-Time Action Detection in Video Surveillance using Sub-Action Descriptor with Multi-CNN
Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer
CAMREP- Concordia Action and Motion Repository
Summarization of User-Generated Sports Video by Using Deep Action Recognition Features
A Grassmannian Approach to Zero-Shot Learning for Network Intrusion Detection
Human Action Forecasting by Learning Task Grammars
Viewpoint Invariant Action Recognition using RGB-D Videos
Multi-Label Zero-Shot Human Action Recognition via Joint Latent Ranking Embedding
Zero-Shot Learning to Manage a Large Number of Place-Specific Compressive Change Classifiers
Supervising Unsupervised Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.