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.
Vandermonde Trajectory Bounds for Linear Companion Systems
Text Classification in the Wild: a Large-scale Long-tailed Name Normalization Dataset
Credal Bayesian Deep Learning
Table Tennis Stroke Detection and Recognition Using Ball Trajectory Data
Dynamic Spatial-temporal Hypergraph Convolutional Network for Skeleton-based Action Recognition
Self-supervised Action Representation Learning from Partial Spatio-Temporal Skeleton Sequences
Video Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer
Syntactic Structure Processing in the Brain while Listening
SupSiam: Non-contrastive Auxiliary Loss for Learning from Molecular Conformers
Frustratingly Simple but Effective Zero-shot Detection and Segmentation: Analysis and a Strong Baseline
Exploring Navigation Maps for Learning-Based Motion Prediction
A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
LiT Tuned Models for Efficient Species Detection
Divergence-Based Domain Transferability for Zero-Shot Classification
Data-Driven Stochastic Motion Evaluation and Optimization with Image by Spatially-Aligned Temporal Encoding
Zero-Knowledge Zero-Shot Learning for Novel Visual Category Discovery
Zero-Shot Learning for Requirements Classification: An Exploratory Study
Diverse Human Motion Prediction Guided by Multi-Level Spatial-Temporal Anchors
ChemVise: Maximizing Out-of-Distribution Chemical Detection with the Novel Application of Zero-Shot Learning
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
A Systematic Evaluation and Benchmark for Embedding-Aware Generative Models: Features, Models, and Any-shot Scenarios
Is ChatGPT a General-Purpose Natural Language Processing Task Solver?
Diversity is Definitely Needed: Improving Model-Agnostic Zero-shot Classification via Stable Diffusion
HumanMAC: Masked Motion Completion for Human Motion Prediction
CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
AIM: Adapting Image Models for Efficient Video Action Recognition
Spatiotemporal Decouple-and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition
Pyramid Self-attention Polymerization Learning for Semi-supervised Skeleton-based Action Recognition
Vision Transformer-based Feature Extraction for Generalized Zero-Shot Learning
Physics Constrained Motion Prediction with Uncertainty Quantification
Vectorized Scenario Description and Motion Prediction for Scenario-Based Testing
Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization
Correspondence-free online human motion retargeting
Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization
Skeleton-based Human Action Recognition via Convolutional Neural Networks (CNN)
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.