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.
An Information-rich Sampling Technique over Spatio-Temporal CNN for Classification of Human Actions in Videos
3D ResNet with Ranking Loss Function for Abnormal Activity Detection in Videos
Action Graphs: Weakly-supervised Action Localization with Graph Convolution Networks
Fine-Tuning BERT for Schema-Guided Zero-Shot Dialogue State Tracking
Domain segmentation and adjustment for generalized zero-shot learning
Modality Compensation Network: Cross-Modal Adaptation for Action Recognition
Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages
Path Planning in Dynamic Environments using Generative RNNs and Monte Carlo Tree Search
Human Action Performance using Deep Neuro-Fuzzy Recurrent Attention Model
UniPose: Unified Human Pose Estimation in Single Images and Videos
Zero-Shot Activity Recognition with Videos
Weakly Supervised Temporal Action Localization Using Deep Metric Learning
Unsupervised Sentiment Analysis for Code-mixed Data
Context-Aware Cross-Attention for Skeleton-Based Human Action Recognition
Cyber Attack Detection thanks to Machine Learning Algorithms
Cluster-based Zero-shot learning for multivariate data
Perception and Navigation in Autonomous Systems in the Era of Learning: A Survey
Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs
VisionNet: A Drivable-space-based Interactive Motion Prediction Network for Autonomous Driving
PGCN-TCA: Pseudo Graph Convolutional Network With Temporal and Channel-Wise Attention for Skeleton-Based Action Recognition
A System for Real-Time Interactive Analysis of Deep Learning Training
Can x2vec Save Lives? Integrating Graph and Language Embeddings for Automatic Mental Health Classification
Human Action Recognition and Assessment via Deep Neural Network Self-Organization
Zero-Shot Reinforcement Learning with Deep Attention Convolutional Neural Networks
Teaching a New Dog Old Tricks: Resurrecting Multilingual Retrieval Using Zero-shot Learning
Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition
DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition
Vertex Feature Encoding and Hierarchical Temporal Modeling in a Spatial-Temporal Graph Convolutional Network for Action Recognition
Locality and compositionality in zero-shot learning
Self-Attention Network for Skeleton-based Human Action Recognition
Contextually Plausible and Diverse 3D Human Motion Prediction
A Probabilistic approach for Learning Embeddings without Supervision
Transductive Zero-Shot Learning for 3D Point Cloud Classification
Mimetics: Towards Understanding Human Actions Out of Context
Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.