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.
Few-Shot Generative Conversational Query Rewriting
Graph-based Visual-Semantic Entanglement Network for Zero-shot Image Recognition
Unsupervised Transfer Learning with Self-Supervised Remedy
Motion Prediction using Trajectory Sets and Self-Driving Domain Knowledge
MultiXNet: Multiclass Multistage Multimodal Motion Prediction
Attribute-Induced Bias Eliminating for Transductive Zero-Shot Learning
Complex Sequential Understanding through the Awareness of Spatial and Temporal Concepts
Reconstructing undersampled photoacoustic microscopy images using deep learning
Spatiotemporal motion prediction in free-breathing liver scans via a recurrent multi-scale encoder decoder
Improving Generalized Zero-Shot Learning by Semantic Discriminator
Language Models are Few-Shot Learners
Algorithm Selection Framework for Cyber Attack Detection
AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings
Unifying Few- and Zero-Shot Egocentric Action Recognition
DeepSSM: Deep State-Space Model for 3D Human Motion Prediction
RV-FuseNet: Range View Based Fusion of Time-Series LiDAR Data for Joint 3D Object Detection and Motion Forecasting
A Better Use of Audio-Visual Cues: Dense Video Captioning with Bi-modal Transformer
Graph Partitioning and Graph Neural Network based Hierarchical Graph Matching for Graph Similarity Computation
CoSimGNN: Towards Large-scale Graph Similarity Computation
Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition
Cross-Conditioned Recurrent Networks for Long-Term Synthesis of Inter-Person Human Motion Interactions
Project RISE: Recognizing Industrial Smoke Emissions
A Biologically Inspired Feature Enhancement Framework for Zero-Shot Learning
3DV: 3D Dynamic Voxel for Action Recognition in Depth Video
Skeleton-Aware Networks for Deep Motion Retargeting
Generative Model-driven Structure Aligning Discriminative Embeddings for Transductive Zero-shot Learning
Transforming task representations to perform novel tasks
An empirical comparison of deep-neural-network architectures for next activity prediction using context-enriched process event logs
CoMoGCN: Coherent Motion Aware Trajectory Prediction with Graph Representation
Zero-Shot Transfer Learning with Synthesized Data for Multi-Domain Dialogue State Tracking
An Ensemble Deep Learning-based Cyber-Attack Detection in Industrial Control System
A Semantics-Guided Graph Convolutional Network for Skeleton-Based Action Recognition
An Empirical Study of Pre-trained Transformers for Arabic Information Extraction
A Novel Perspective to Zero-shot Learning: Towards an Alignment of Manifold Structures via Semantic Feature Expansion
Zero-Shot Learning and its Applications from Autonomous Vehicles to COVID-19 Diagnosis: A Review
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.