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.
Generalized Zero-Shot Domain Adaptation via Coupled Conditional Variational Autoencoders
Vision and Inertial Sensing Fusion for Human Action Recognition : A Review
Improving Skeleton-based Action Recognitionwith Robust Spatial and Temporal Features
Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning
Predicting heave and surge motions of a semi-submersible with neural networks
Traffic Control Gesture Recognition for Autonomous Vehicles
Hierarchical Action Classification with Network Pruning
Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge
Mix Dimension in Poincaré Geometry for 3D Skeleton-based Action Recognition
Dynamic GCN: Context-enriched Topology Learning for Skeleton-based Action Recognition
Toward Zero-Shot Unsupervised Image-to-Image Translation
Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches
History Repeats Itself: Human Motion Prediction via Motion Attention
Zero-Shot Recognition through Image-Guided Semantic Classification
ZSCRGAN: A GAN-based Expectation Maximization Model for Zero-Shot Retrieval of Images from Textual Descriptions
Towards Recognizing Unseen Categories in Unseen Domains
Depthwise Spatio-Temporal STFT Convolutional Neural Networks for Human Action Recognition
Perceptron Synthesis Network: Rethinking the Action Scale Variances in Videos
Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020
Hierarchical Contrastive Motion Learning for Video Action Recognition
Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learning
Two-Level Adversarial Visual-Semantic Coupling for Generalized Zero-shot Learning
Personalized Face Modeling for Improved Face Reconstruction and Motion Retargeting
COBE: Contextualized Object Embeddings from Narrated Instructional Video
TinyVIRAT: Low-resolution Video Action Recognition
IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos
Multitask Non-Autoregressive Model for Human Motion Prediction
Adversarial Background-Aware Loss for Weakly-supervised Temporal Activity Localization
Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition
Representation Learning via Adversarially-Contrastive Optimal Transport
Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets
Invertible Zero-Shot Recognition Flows
Learning Speech Representations from Raw Audio by Joint Audiovisual Self-Supervision
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition
Long-term Human Motion Prediction with Scene Context
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.