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.
Spatio-Temporal Human Action Recognition Modelwith Flexible-interval Sampling and Normalization
Conditional Temporal Variational AutoEncoder for Action Video Prediction
DexMV: Imitation Learning for Dexterous Manipulation from Human Videos
Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition
Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognition
Development of Human Motion Prediction Strategy using Inception Residual Block
Pose is all you need: The pose only group activity recognition system (POGARS)
AutoVideo: An Automated Video Action Recognition System
Skeleton-Contrastive 3D Action Representation Learning
Temporal Action Localization Using Gated Recurrent Units
A Unified Model for Zero-shot Music Source Separation, Transcription and Synthesis
SLAMP: Stochastic Latent Appearance and Motion Prediction
Elaborative Rehearsal for Zero-shot Action Recognition
Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning
Non-local Graph Convolutional Network for joint Activity Recognition and Motion Prediction
Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learning
FREE: Feature Refinement for Generalized Zero-Shot Learning
Security of Distributed Parameter Cyber-Physical Systems: Cyber-Attack Detection in Linear Parabolic PDEs
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing
Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization
Transferable Knowledge-Based Multi-Granularity Aggregation Network for Temporal Action Localization: Submission to ActivityNet Challenge 2021
Enriching Local and Global Contexts for Temporal Action Localization
A New Split for Evaluating True Zero-Shot Action Recognition
What Remains of Visual Semantic Embeddings
Language Models as Zero-shot Visual Semantic Learners
Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition
External-Memory Networks for Low-Shot Learning of Targets in Forward-Looking-Sonar Imagery
AgileGAN: stylizing portraits by inversion-consistent transfer learning
UNIK: A Unified Framework for Real-world Skeleton-based Action Recognition
Agent-Environment Network for Temporal Action Proposal Generation
Exploiting generative self-supervised learning for the assessment of biological images with lack of annotations: a COVID-19 case-study
STAR: Sparse Transformer-based Action Recognition
Training for temporal sparsity in deep neural networks, application in video processing
Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.