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.
A Generalized Zero-Shot Framework for Emotion Recognition from Body Gestures
MS$^2$L: Multi-Task Self-Supervised Learning for Skeleton Based Action Recognition
SDMTL: Semi-Decoupled Multi-grained Trajectory Learning for 3D human motion prediction
Data Agnostic RoBERTa-based Natural Language to SQL Query Generation
AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data
Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning
Learning Clusterable Visual Features for Zero-Shot Recognition
ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization
Reconfigurable Cyber-Physical System for Lifestyle Video-Monitoring via Deep Learning
Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning
Motion Prediction Using Temporal Inception Module
Generative Model-Enhanced Human Motion Prediction
An Empirical Study on Large-Scale Multi-Label Text Classification Including Few and Zero-Shot Labels
A Variational Information Bottleneck Based Method to Compress Sequential Networks for Human Action Recognition
Taking Modality-free Human Identification as Zero-shot Learning
Data-Efficient Pretraining via Contrastive Self-Supervision
Cross-Lingual Transfer Learning for Complex Word Identification
InHARD - Industrial Human Action Recognition Dataset in the Context of Industrial Collaborative Robotics
Knowledge Fusion Transformers for Video Action Recognition
A Prototype-Based Generalized Zero-Shot Learning Framework for Hand Gesture Recognition
Motion Planning Combines Psychological Safety and Motion Prediction for a Sense Motive Robot
Event-based Action Recognition Using Timestamp Image Encoding Network
PERF-Net: Pose Empowered RGB-Flow Net
From Pixel to Patch: Synthesize Context-aware Features for Zero-shot Semantic Segmentation
Attribute Propagation Network for Graph Zero-shot Learning
Learning Unseen Emotions from Gestures via Semantically-Conditioned Zero-Shot Perception with Adversarial Autoencoders
Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning
Knowledge Guided Learning: Towards Open Domain Egocentric Action Recognition with Zero Supervision
Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
Prior Knowledge about Attributes: Learning a More Effective Potential Space for Zero-Shot Recognition
Visually Analyzing and Steering Zero Shot Learning
L2-Constrained RemNet for Camera Model Identification and Image Manipulation Detection
HSFM-$Σ$nn: Combining a Feedforward Motion Prediction Network and Covariance Prediction
Generalized Zero-Shot Learning via VAE-Conditioned Generative Flow
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.