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.
A Ligand-and-structure Dual-driven Deep Learning Method for the Discovery of Highly Potent GnRH1R Antagonist to treat Uterine Diseases
Real-Time Elderly Monitoring for Senior Safety by Lightweight Human Action Recognition
Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning
HTNet: Anchor-free Temporal Action Localization with Hierarchical Transformers
Collaborating Domain-shared and Target-specific Feature Clustering for Cross-domain 3D Action Recognition
Temporal and cross-modal attention for audio-visual zero-shot learning
Time Is MattEr: Temporal Self-supervision for Video Transformers
Don't Stop Learning: Towards Continual Learning for the CLIP Model
Contributions of Shape, Texture, and Color in Visual Recognition
Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition
ELECTRA is a Zero-Shot Learner, Too
Stroke-Based Autoencoders: Self-Supervised Learners for Efficient Zero-Shot Chinese Character Recognition
LAVA: Language Audio Vision Alignment for Contrastive Video Pre-Training
Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space
Proposal-Free Temporal Action Detection via Global Segmentation Mask Learning
Forcing the Whole Video as Background: An Adversarial Learning Strategy for Weakly Temporal Action Localization
A Personalized Zero-Shot ECG Arrhythmia Monitoring System: From Sparse Representation Based Domain Adaption to Energy Efficient Abnormal Beat Detection for Practical ECG Surveillance
ReAct: Temporal Action Detection with Relational Queries
Contrastive Adapters for Foundation Model Group Robustness
Skeletal Human Action Recognition using Hybrid Attention based Graph Convolutional Network
Learning Continuous Grasping Function with a Dexterous Hand from Human Demonstrations
Few-shot training LLMs for project-specific code-summarization
Boosting Zero-shot Learning via Contrastive Optimization of Attribute Representations
Contrastive Learning from Spatio-Temporal Mixed Skeleton Sequences for Self-Supervised Skeleton-Based Action Recognition
GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning
Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer
DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learning
Learning Disentangled Representations for Controllable Human Motion Prediction
Large-scale Robustness Analysis of Video Action Recognition Models
General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States
Back to MLP: A Simple Baseline for Human Motion Prediction
Noise and Edge Based Dual Branch Image Manipulation Detection
Golfer: Trajectory Prediction with Masked Goal Conditioning MnM Network
Spatial Transformer Network with Transfer Learning for Small-scale Fine-grained Skeleton-based Tai Chi Action Recognition
BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.