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.
Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
Preserving Semantic Relations for Zero-Shot Learning
Analysis of Hand Segmentation in the Wild
Sparse Adversarial Perturbations for Videos
A Comparative Study of Pairwise Learning Methods based on Kernel Ridge Regression
Learning clip representations for skeleton-based 3d action recognition
Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition
2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning
Real-Time End-to-End Action Detection with Two-Stream Networks
Glimpse Clouds: Human Activity Recognition from Unstructured Feature Points
Learning to Play with Intrinsically-Motivated Self-Aware Agents
Emergence of Structured Behaviors from Curiosity-Based Intrinsic Motivation
Learning Representative Temporal Features for Action Recognition
Fisherposes for Human Action Recognition Using Kinect Sensor Data
Relational Autoencoder for Feature Extraction
Boosting Image Forgery Detection using Resampling Features and Copy-move analysis
Deep Learning for Malicious Flow Detection
Zero-Shot Kernel Learning
Musical Chair: Efficient Real-Time Recognition Using Collaborative IoT Devices
Human Action Adverb Recognition: ADHA Dataset and A Three-Stream Hybrid Model
DeepProcess: Supporting business process execution using a MANN-based recommender system
Deep-Temporal LSTM for Daily Living Action Recognition
Action Recognition with Spatio-Temporal Visual Attention on Skeleton Image Sequences
Histogram of Oriented Depth Gradients for Action Recognition
A Generative Approach to Zero-Shot and Few-Shot Action Recognition
Class label autoencoder for zero-shot learning
Let's Dance: Learning From Online Dance Videos
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
DiscrimNet: Semi-Supervised Action Recognition from Videos using Generative Adversarial Networks
How would surround vehicles move? A Unified Framework for Maneuver Classification and Motion Prediction
Multivariate LSTM-FCNs for Time Series Classification
Semi-supervised Fisher vector network
Fully-Coupled Two-Stream Spatiotemporal Networks for Extremely Low Resolution Action Recognition
Moments in Time Dataset: one million videos for event understanding
Ensemble One-dimensional Convolution Neural Networks for Skeleton-based Action Recognition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.