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.
JOKR: Joint Keypoint Representation for Unsupervised Cross-Domain Motion Retargeting
BABEL: Bodies, Action and Behavior with English Labels
Disentangling Semantic-to-visual Confusion for Zero-shot Learning
Temporal Consistency Checks to Detect LiDAR Spoofing Attacks on Autonomous Vehicle Perception
Zero-sample surface defect detection and classification based on semantic feedback neural network
Relation Modeling in Spatio-Temporal Action Localization
Scene Transformer: A unified architecture for predicting multiple agent trajectories
Flow Guided Transformable Bottleneck Networks for Motion Retargeting
Towards User-Driven Neural Machine Translation
Conterfactual Generative Zero-Shot Semantic Segmentation
A Framework to Enhance Generalization of Deep Metric Learning methods using General Discriminative Feature Learning and Class Adversarial Neural Networks
Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers
Learning from Multiple Noisy Partial Labelers
Phase retrieval with physics informed zero-shot learning
Multilingual Neural Semantic Parsing for Low-Resourced Languages
A structured latent space for human body motion generation
Transferring Knowledge from Text to Video: Zero-Shot Anticipation for Procedural Actions
How to Adapt Your Pretrained Multilingual Model to 1600 Languages
TSI: Temporal Saliency Integration for Video Action Recognition
Long Term Object Detection and Tracking in Collaborative Learning Environments
Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning
Independent Prototype Propagation for Zero-Shot Compositionality
Pho(SC)-CTC -- A Hybrid Approach Towards Zero-shot Word Image Recognition
Meta-HAR: Federated Representation Learning for Human Activity Recognition
Inertial Sensor Data To Image Encoding For Human Action Recognition
pRSL: Interpretable Multi-label Stacking by Learning Probabilistic Rules
SSAN: Separable Self-Attention Network for Video Representation Learning
The Imaginative Generative Adversarial Network: Automatic Data Augmentation for Dynamic Skeleton-Based Hand Gesture and Human Action Recognition
GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition
Temporal Action Proposal Generation with Transformers
FineAction: A Fine-Grained Video Dataset for Temporal Action Localization
Real-time Human Action Recognition Using Locally Aggregated Kinematic-Guided Skeletonlet and Supervised Hashing-by-Analysis Model
Compositional Fine-Grained Low-Shot Learning
Data-driven Unknown-input Observers and State Estimation
An Attractor-Guided Neural Networks for Skeleton-Based Human Motion Prediction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.