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.
STAR-Transformer: A Spatio-temporal Cross Attention Transformer for Human Action Recognition
Improving Transfer Learning with a Dual Image and Video Transformer for Multi-label Movie Trailer Genre Classification
Rebalanced Zero-shot Learning
Visual Classification via Description from Large Language Models
Towards a Unified Multi-Dimensional Evaluator for Text Generation
DG-STGCN: Dynamic Spatial-Temporal Modeling for Skeleton-based Action Recognition
Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction
MotionBERT: A Unified Perspective on Learning Human Motion Representations
It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training
Contrastive Training Improves Zero-Shot Classification of Semi-structured Documents
Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning
Pose-Guided Graph Convolutional Networks for Skeleton-Based Action Recognition
Non-intrusive Load Monitoring based on Self-supervised Learning
KP-RNN: A Deep Learning Pipeline for Human Motion Prediction and Synthesis of Performance Art
Improving Data-Efficient Fossil Segmentation via Model Editing
APE: Aligning Pretrained Encoders to Quickly Learn Aligned Multimodal Representations
LOCL: Learning Object-Attribute Composition using Localization
Focal and Global Spatial-Temporal Transformer for Skeleton-based Action Recognition
AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation
Self-omics: A Self-supervised Learning Framework for Multi-omics Cancer Data
LASP: Text-to-Text Optimization for Language-Aware Soft Prompting of Vision & Language Models
Cross-identity Video Motion Retargeting with Joint Transformation and Synthesis
HyperHawkes: Hypernetwork based Neural Temporal Point Process
Application-Driven AI Paradigm for Human Action Recognition
Alignment-guided Temporal Attention for Video Action Recognition
Prompt-guided Scene Generation for 3D Zero-Shot Learning
REST: REtrieve & Self-Train for generative action recognition
Hierarchical Cyber-Attack Detection in Large-Scale Interconnected Systems
CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention
RALACs: Action Recognition in Autonomous Vehicles using Interaction Encoding and Optical Flow
Motion Transformer with Global Intention Localization and Local Movement Refinement
Multi-dataset Training of Transformers for Robust Action Recognition
Exploring Attention GAN for Vehicle Motion Prediction
Lex2Sent: A bagging approach to unsupervised sentiment analysis
View-Invariant Skeleton-based Action Recognition via Global-Local Contrastive Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.