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.
FewCLUE: A Chinese Few-shot Learning Evaluation Benchmark
Multi-Label Generalized Zero Shot Learning for the Classification of Disease in Chest Radiographs
Probabilistic Human Motion Prediction via A Bayesian Neural Network
Zero-Shot Compositional Concept Learning
Structured Latent Embeddings for Recognizing Unseen Classes in Unseen Domains
Learn from Anywhere: Rethinking Generalized Zero-Shot Learning with Limited Supervision
RGB Stream Is Enough for Temporal Action Detection
Uncertainty-aware Human Motion Prediction
Mitigating Generation Shifts for Generalized Zero-Shot Learning
ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation
Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Network
Ensemble of Loss Functions to Improve Generalizability of Deep Metric Learning methods
Generating Synthetic Training Data for Deep Learning-Based UAV Trajectory Prediction
Language-Level Semantics Conditioned 3D Point Cloud Segmentation
VideoLightFormer: Lightweight Action Recognition using Transformers
Improving Human Motion Prediction Through Continual Learning
Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition
Zero-shot Learning with Class Description Regularization
Benchmarking Knowledge-driven Zero-shot Learning
Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition
Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversals
Hear Me Out: Fusional Approaches for Audio Augmented Temporal Action Localization
DenseTNT: Waymo Open Dataset Motion Prediction Challenge 1st Place Solution
Exploring Temporal Context and Human Movement Dynamics for Online Action Detection in Videos
Generalized Zero-Shot Learning using Multimodal Variational Auto-Encoder with Semantic Concepts
Exploring Stronger Feature for Temporal Action Localization
Zero-Shot Joint Modeling of Multiple Spoken-Text-Style Conversion Tasks using Switching Tokens
NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles
Transfer Learning of Deep Spatiotemporal Networks to Model Arbitrarily Long Videos of Seizures
Two-Stream Consensus Network: Submission to HACS Challenge 2021 Weakly-Supervised Learning Track
STEP-EZ: Syntax Tree guided semantic ExPlanation for Explainable Zero-shot modeling of clinical depression symptoms from text
Zero-shot learning approach to adaptive Cybersecurity using Explainable AI
Weakly-Supervised Temporal Action Localization Through Local-Global Background Modeling
Proposal Relation Network for Temporal Action Detection
End-to-end Temporal Action Detection with Transformer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.