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.
ZeroGen: Efficient Zero-shot Learning via Dataset Generation
ActionFormer: Localizing Moments of Actions with Transformers
When Did It Happen? Duration-informed Temporal Localization of Narrated Actions in Vlogs
Video-driven Neural Physically-based Facial Asset for Production
Bias-Eliminated Semantic Refinement for Any-Shot Learning
OWL (Observe, Watch, Listen): Audiovisual Temporal Context for Localizing Actions in Egocentric Videos
Zero Shot Learning for Predicting Energy Usage of Buildings in Sustainable Design
Locating and Editing Factual Associations in GPT
Generating Training Data with Language Models: Towards Zero-Shot Language Understanding
Joint-bone Fusion Graph Convolutional Network for Semi-supervised Skeleton Action Recognition
CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensors
Cedille: A large autoregressive French language model
Bootstrapped Representation Learning for Skeleton-Based Action Recognition
Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition
Co-training Improves Prompt-based Learning for Large Language Models
GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records
ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation
Crowd-powered Face Manipulation Detection: Fusing Human Examiner Decisions
Assessment of DeepONet for reliability analysis of stochastic nonlinear dynamical systems
Benchmarking Conventional Vision Models on Neuromorphic Fall Detection and Action Recognition Dataset
A Transfer Learning and Optimized CNN Based Intrusion Detection System for Internet of Vehicles
Clinical-Longformer and Clinical-BigBird: Transformers for long clinical sequences
How Robust are Discriminatively Trained Zero-Shot Learning Models?
Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition
Semantically Video Coding: Instill Static-Dynamic Clues into Structured Bitstream for AI Tasks
Compound Projection Learning for Bridging Seen and Unseen Objects
ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization
Learning Hierarchical Graph Representation for Image Manipulation Detection
Real-World Graph Convolution Networks (RW-GCNs) for Action Recognition in Smart Video Surveillance
Towards Zero-shot Sign Language Recognition
HardBoost: Boosting Zero-Shot Learning with Hard Classes
Semantic Labeling of Human Action For Visually Impaired And Blind People Scene Interaction
Zero-Shot and Few-Shot Classification of Biomedical Articles in Context of the COVID-19 Pandemic
Spatio-Temporal Tuples Transformer for Skeleton-Based Action Recognition
Motion Prediction via Joint Dependency Modeling in Phase Space
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.