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.
Multi-target prediction for dummies using two-branch neural networks
AmericasNLI: Evaluating Zero-shot Natural Language Understanding of Pretrained Multilingual Models in Truly Low-resource Languages
Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation
Does language help generalization in vision models?
Motion Prediction Performance Analysis for Autonomous Driving Systems and the Effects of Tracking Noise
Image Manipulation Detection by Multi-View Multi-Scale Supervision
Spatiotemporal Entropy Model is All You Need for Learned Video Compression
Event-based Timestamp Image Encoding Network for Human Action Recognition and Anticipation
Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition
Learning Robust Visual-semantic Mapping for Zero-shot Learning
Holistic Image Manipulation Detection using Pixel Co-occurrence Matrices
Evaluating Pre-Trained Models for User Feedback Analysis in Software Engineering: A Study on Classification of App-Reviews
Zero-Shot Learning on 3D Point Cloud Objects and Beyond
Temporal Consistency Two-Stream CNN for Human Motion Prediction
Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections
Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics
Detection of Network and Sensor Cyber-Attacks in Platoons of Cooperative Autonomous Vehicles: a Sliding-Mode Observer Approach
ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization
Self-Supervised Learning for Semi-Supervised Temporal Action Proposal
Modern Hopfield Networks for Few- and Zero-Shot Reaction Template Prediction
Hippocampus-heuristic Character Recognition Network for Zero-shot Learning
Adaptive Mutual Supervision for Weakly-Supervised Temporal Action Localization
Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning
Self-supervised Video Representation Learning by Context and Motion Decoupling
Low-Resource Neural Machine Translation for Southern African Languages
Composable Augmentation Encoding for Video Representation Learning
Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation
Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context
Contrastive Embedding for Generalized Zero-Shot Learning
CoLA: Weakly-Supervised Temporal Action Localization with Snippet Contrastive Learning
Rectification-based Knowledge Retention for Continual Learning
No frame left behind: Full Video Action Recognition
A Simple Approach for Zero-Shot Learning based on Triplet Distribution Embeddings
ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization
Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.