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.
ABN: Agent-Aware Boundary Networks for Temporal Action Proposal Generation
SISL:Self-Supervised Image Signature Learning for Splicing Detection and Localization
Efficient Language Modeling with Sparse all-MLP
Context-LSTM: a robust classifier for video detection on UCF101
OpenTAL: Towards Open Set Temporal Action Localization
End-to-End Semantic Video Transformer for Zero-Shot Action Recognition
Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis
HealthPrompt: A Zero-shot Learning Paradigm for Clinical Natural Language Processing
Geodesic Multi-Modal Mixup for Robust Fine-Tuning
Universal Prototype Transport for Zero-Shot Action Recognition and Localization
A Gating Model for Bias Calibration in Generalized Zero-shot Learning
A Lightweight and Detector-free 3D Single Object Tracker on Point Clouds
MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning
Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attention
Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language
Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation
Social-Implicit: Rethinking Trajectory Prediction Evaluation and The Effectiveness of Implicit Maximum Likelihood Estimation
Cluster-based Contrastive Disentangling for Generalized Zero-Shot Learning
Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion
Spatio-Temporal Gating-Adjacency GCN for Human Motion Prediction
BatchFormer: Learning to Explore Sample Relationships for Robust Representation Learning
3D Human Motion Prediction: A Survey
Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning
H4D: Human 4D Modeling by Learning Neural Compositional Representation
Exploring Hierarchical Graph Representation for Large-Scale Zero-Shot Image Classification
3D Skeleton-based Human Motion Prediction with Manifold-Aware GAN
Domain Knowledge-Informed Self-Supervised Representations for Workout Form Assessment
Spatiotemporal Transformer Attention Network for 3D Voxel Level Joint Segmentation and Motion Prediction in Point Cloud
Continuous Human Action Recognition for Human-Machine Interaction: A Review
SemSup: Semantic Supervision for Simple and Scalable Zero-shot Generalization
On Modality Bias Recognition and Reduction
Absolute Zero-Shot Learning
Delving Deep into One-Shot Skeleton-based Action Recognition with Diverse Occlusions
Path-Aware Graph Attention for HD Maps in Motion Prediction
Automated Attack Synthesis by Extracting Finite State Machines from Protocol Specification Documents
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.