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.
BLP -- Boundary Likelihood Pinpointing Networks for Accurate Temporal Action Localization
Hide-and-Seek: A Data Augmentation Technique for Weakly-Supervised Localization and Beyond
StNet: Local and Global Spatial-Temporal Modeling for Action Recognition
Leveraging Random Label Memorization for Unsupervised Pre-Training
Data-driven Perception of Neuron Point Process with Unknown Unknowns
Hierarchical Long Short-Term Concurrent Memory for Human Interaction Recognition
Ionospheric activity prediction using convolutional recurrent neural networks
DeepGRU: Deep Gesture Recognition Utility
Random Temporal Skipping for Multirate Video Analysis
Informed Democracy: Voting-based Novelty Detection for Action Recognition
ActionXPose: A Novel 2D Multi-view Pose-based Algorithm for Real-time Human Action Recognition
Imagination Based Sample Construction for Zero-Shot Learning
Semi-unsupervised Learning of Human Activity using Deep Generative Models
Cascaded Pyramid Mining Network for Weakly Supervised Temporal Action Localization
$A^2$-Nets: Double Attention Networks
Real-time Action Recognition with Dissimilarity-based Training of Specialized Module Networks
Domain-Invariant Projection Learning for Zero-Shot Recognition
Transferrable Feature and Projection Learning with Class Hierarchy for Zero-Shot Learning
Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
Learning the Compositional Spaces for Generalized Zero-shot Learning
Combined Static and Motion Features for Deep-Networks Based Activity Recognition in Videos
Cross-Modal and Hierarchical Modeling of Video and Text
Integrating kinematics and environment context into deep inverse reinforcement learning for predicting off-road vehicle trajectories
Hyper-Process Model: A Zero-Shot Learning algorithm for Regression Problems based on Shape Analysis
CSI-Net: Unified Human Body Characterization and Pose Recognition
Towards High Resolution Video Generation with Progressive Growing of Sliced Wasserstein GANs
Task-Oriented Hand Motion Retargeting for Dexterous Manipulation Imitation
Representation Flow for Action Recognition
Interpretable Spatio-temporal Attention for Video Action Recognition
Zero-Shot Learning Based Approach For Medieval Word Recognition Using Deep-Learned Features
Rate-Accuracy Trade-Off In Video Classification With Deep Convolutional Neural Networks
From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process
A Probabilistic Semi-Supervised Approach to Multi-Task Human Activity Modeling
Online Cyber-Attack Detection in Smart Grid: A Reinforcement Learning Approach
Part-based Graph Convolutional Network for Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.