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.
CMSN: Continuous Multi-stage Network and Variable Margin Cosine Loss for Temporal Action Proposal Generation
Deep-Aligned Convolutional Neural Network for Skeleton-based Action Recognition and Segmentation
Fast Learning of Temporal Action Proposal via Dense Boundary Generator
Learning Graph Convolutional Network for Skeleton-based Human Action Recognition by Neural Searching
Disentangle, align and fuse for multimodal and semi-supervised image segmentation
Predicting Long-Term Skeletal Motions by a Spatio-Temporal Hierarchical Recurrent Network
Multiple Futures Prediction
Temporal Action Localization using Long Short-Term Dependency
Chirality Nets for Human Pose Regression
A Hamilton-Jacobi Reachability-Based Framework for Predicting and Analyzing Human Motion for Safe Planning
Transferring neural speech waveform synthesizers to musical instrument sounds generation
GRIP: Graph-based Interaction-aware Trajectory Prediction
Human Action Recognition Using Deep Multilevel Multimodal (M2) Fusion of Depth and Inertial Sensors
Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples
ATZSL: Defensive Zero-Shot Recognition in the Presence of Adversaries
Towards Train-Test Consistency for Semi-supervised Temporal Action Localization
Cross-Lingual Vision-Language Navigation
Hierarchical Prototype Learning for Zero-Shot Recognition
Convolutional Prototype Learning for Zero-Shot Recognition
Human Action Recognition in Drone Videos using a Few Aerial Training Examples
Zero-shot Learning via Simultaneous Generating and Learning
Zero-Shot Recognition via Optimal Transport
Structured Prediction Helps 3D Human Motion Modelling
Looking Ahead: Anticipating Pedestrians Crossing with Future Frames Prediction
Coordinated Joint Multimodal Embeddings for Generalized Audio-Visual Zeroshot Classification and Retrieval of Videos
Discrete Residual Flow for Probabilistic Pedestrian Behavior Prediction
Zero-shot Policy Learning with Spatial Temporal RewardDecomposition on Contingency-aware Observation
TrajectoryNet: a new spatio-temporal feature learning network for human motion prediction
Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
Imitating by generating: deep generative models for imitation of interactive tasks
How to Not Measure Disentanglement
Generating Human Action Videos by Coupling 3D Game Engines and Probabilistic Graphical Models
A Theory of Relation Learning and Cross-domain Generalization
Deep Independently Recurrent Neural Network (IndRNN)
A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.