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.
Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision
CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directions
Topology-aware Convolutional Neural Network for Efficient Skeleton-based Action Recognition
Real-time Collision Risk Estimation based on Stochastic Reachability Spaces
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition
DCAN: Improving Temporal Action Detection via Dual Context Aggregation
MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection
A Survey of Deep Learning for Low-Shot Object Detection
Prototypical Model with Novel Information-theoretic Loss Function for Generalized Zero Shot Learning
Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition
STSM: Spatio-Temporal Shift Module for Efficient Action Recognition
VT-CLIP: Enhancing Vision-Language Models with Visual-guided Texts
YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone
TransZero: Attribute-guided Transformer for Zero-Shot Learning
Hierarchical Neural Implicit Pose Network for Animation and Motion Retargeting
3rd Place Solution for NeurIPS 2021 Shifts Challenge: Vehicle Motion Prediction
3DVNet: Multi-View Depth Prediction and Volumetric Refinement
Graph Convolutional Module for Temporal Action Localization in Videos
Dyadic Human Motion Prediction
Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning
LatentHuman: Shape-and-Pose Disentangled Latent Representation for Human Bodies
Anonymization for Skeleton Action Recognition
Zero-Shot Semantic Segmentation via Spatial and Multi-Scale Aware Visual Class Embedding
ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic
3D Compositional Zero-shot Learning with DeCompositional Consensus
MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction
Make an Omelette with Breaking Eggs: Zero-Shot Learning for Novel Attribute Synthesis
Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fields
3D Pose Estimation and Future Motion Prediction from 2D Images
Using Fictitious Class Representations to Boost Discriminative Zero-Shot Learners
Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains
ML-Decoder: Scalable and Versatile Classification Head
Learning from Temporal Gradient for Semi-supervised Action Recognition
Background-Click Supervision for Temporal Action Localization
Multi-Person 3D Motion Prediction with Multi-Range Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.