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.
Event Extraction by Answering (Almost) Natural Questions
Empirical Bayes Transductive Meta-Learning with Synthetic Gradients
TPNet: Trajectory Proposal Network for Motion Prediction
Action recognition in real-world videos
Spatio-Temporal Dual Affine Differential Invariant for Skeleton-based Action Recognition
Combining Deep Learning Classifiers for 3D Action Recognition
A Spatio-temporal Transformer for 3D Human Motion Prediction
ArTIST: Autoregressive Trajectory Inpainting and Scoring for Tracking
Video Face Manipulation Detection Through Ensemble of CNNs
Cross-lingual Contextualized Topic Models with Zero-shot Learning
Improving Movement Predictions of Traffic Actors in Bird's-Eye View Models using GANs and Differentiable Trajectory Rasterization
Deep Learning Models for Multilingual Hate Speech Detection
SR2CNN: Zero-Shot Learning for Signal Recognition
Spatiotemporal Fusion in 3D CNNs: A Probabilistic View
Improved Residual Networks for Image and Video Recognition
Generative Adversarial Zero-shot Learning via Knowledge Graphs
What and Where: Modeling Skeletons from Semantic and Spatial Perspectives for Action Recognition
Human action recognition with a large-scale brain-inspired photonic computer
Zero-Shot Learning of Text Adventure Games with Sentence-Level Semantics
From Generalized zero-shot learning to long-tail with class descriptors
Disassembling Object Representations without Labels
Safe Learning MPC with Limited Model Knowledge and Data
Handling new target classes in semantic segmentation with domain adaptation
Future Video Synthesis with Object Motion Prediction
Symmetry and Group in Attribute-Object Compositions
Generalized Zero-Shot Learning Via Over-Complete Distribution
Learning Cross-domain Semantic-Visual Relationships for Transductive Zero-Shot Learning
Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting
Weakly-Supervised Action Localization with Expectation-Maximization Multi-Instance Learning
Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learning
CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks
Convolutional Spiking Neural Networks for Spatio-Temporal Feature Extraction
Weakly-Supervised Action Localization by Generative Attention Modeling
CAZSL: Zero-Shot Regression for Pushing Models by Generalizing Through Context
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.