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.
Cyber-resilient Automatic Generation Control for Systems of AC Microgrids
Reference-Limited Compositional Zero-Shot Learning
Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition
SoMoFormer: Social-Aware Motion Transformer for Multi-Person Motion Prediction
Open Vocabulary Multi-Label Classification with Dual-Modal Decoder on Aligned Visual-Textual Features
Spatial Temporal Graph Attention Network for Skeleton-Based Action Recognition
Progressive Cross-modal Knowledge Distillation for Human Action Recognition
Complex-Value Spatio-temporal Graph Convolutional Neural Networks and its Applications to Electric Power Systems AI
Temporal Action Localization with Multi-temporal Scales
Multi-level Contrast Network for Wearables-based Joint Activity Segmentation and Recognition
Prediction of Seismic Intensity Distributions Using Neural Networks
ViT-ReT: Vision and Recurrent Transformer Neural Networks for Human Activity Recognition in Videos
DisenHCN: Disentangled Hypergraph Convolutional Networks for Spatiotemporal Activity Prediction
Two-person Graph Convolutional Network for Skeleton-based Human Interaction Recognition
PSUMNet: Unified Modality Part Streams are All You Need for Efficient Pose-based Action Recognition
Self-supervised Multi-modal Training from Uncurated Image and Reports Enables Zero-shot Oversight Artificial Intelligence in Radiology
Consistency-based Self-supervised Learning for Temporal Anomaly Localization
Generative Action Description Prompts for Skeleton-based Action Recognition
BabyNet: A Lightweight Network for Infant Reaching Action Recognition in Unconstrained Environments to Support Future Pediatric Rehabilitation Applications
Txt2Img-MHN: Remote Sensing Image Generation from Text Using Modern Hopfield Networks
Video-based Human Action Recognition using Deep Learning: A Review
AFE-CNN: 3D Skeleton-based Action Recognition with Action Feature Enhancement
Blockwise Temporal-Spatial Pathway Network
Privacy-Preserving Action Recognition via Motion Difference Quantization
Combined CNN Transformer Encoder for Enhanced Fine-grained Human Action Recognition
Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos
AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy
Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction
Motion-aware Memory Network for Fast Video Salient Object Detection
Skeleton-Parted Graph Scattering Networks for 3D Human Motion Prediction
Cross-Modal Alignment Learning of Vision-Language Conceptual Systems
Learning Prototype via Placeholder for Zero-shot Recognition
AlphaVC: High-Performance and Efficient Learned Video Compression
Unsupervised Domain Adaptation for Video Transformers in Action Recognition
LETS-GZSL: A Latent Embedding Model for Time Series Generalized Zero Shot Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.