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.
Lifelong Graph Learning
Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature
Effective Action Recognition with Embedded Key Point Shifts
DeepSOCIAL: Social Distancing Monitoring and Infection Risk Assessment in COVID-19 Pandemic
Defending Water Treatment Networks: Exploiting Spatio-temporal Effects for Cyber Attack Detection
Two-Stream Networks for Lane-Change Prediction of Surrounding Vehicles
Boundary Uncertainty in a Single-Stage Temporal Action Localization Network
Bias-Awareness for Zero-Shot Learning the Seen and Unseen
Temporal Action Localization with Variance-Aware Networks
What-If Motion Prediction for Autonomous Driving
Towards Improved Human Action Recognition Using Convolutional Neural Networks and Multimodal Fusion of Depth and Inertial Sensor Data
Multidomain Multimodal Fusion For Human Action Recognition Using Inertial Sensors
Revisiting Anchor Mechanisms for Temporal Action Localization
Accuracy and Performance Comparison of Video Action Recognition Approaches
Learning to Abstract and Predict Human Actions
Attribute Prototype Network for Zero-Shot Learning
CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization
Prescriptive Business Process Monitoring for Recommending Next Best Actions
Equivalent Classification Mapping for Weakly Supervised Temporal Action Localization
ConvGRU in Fine-grained Pitching Action Recognition for Action Outcome Prediction
XNAP: Making LSTM-based Next Activity Predictions Explainable by Using LRP
Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
A Deep Dive into Adversarial Robustness in Zero-Shot Learning
DSDNet: Deep Structured self-Driving Network
Adversarial Generative Grammars for Human Activity Prediction
VI-Net: View-Invariant Quality of Human Movement Assessment
Richly Activated Graph Convolutional Network for Robust Skeleton-based Action Recognition
A Boundary Based Out-of-Distribution Classifier for Generalized Zero-Shot Learning
Single-stage intake gesture detection using CTC loss and extended prefix beam search
Group Activity Prediction with Sequential Relational Anticipation Model
Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning
Self-supervised Temporal Discriminative Learning for Video Representation Learning
Boundary Content Graph Neural Network for Temporal Action Proposal Generation
Graph Convolution with Low-rank Learnable Local Filters
Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.