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.
Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time-Series Forecast
PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining
Flamingo: a Visual Language Model for Few-Shot Learning
A Comprehensive Understanding of Code-mixed Language Semantics using Hierarchical Transformer
Contrastive Language-Action Pre-training for Temporal Localization
A Spatio-Temporal Multilayer Perceptron for Gesture Recognition
Zero-Shot Logit Adjustment
Deconstructed Generation-Based Zero-Shot Model
On Leveraging Variational Graph Embeddings for Open World Compositional Zero-Shot Learning
Tweets2Stance: Users stance detection exploiting Zero-Shot Learning Algorithms on Tweets
iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition
Persistent-Transient Duality in Human Behavior Modeling
Unsupervised Human Action Recognition with Skeletal Graph Laplacian and Self-Supervised Viewpoints Invariance
DAME: Domain Adaptation for Matching Entities
A Survey of Video-based Action Quality Assessment
FenceNet: Fine-grained Footwork Recognition in Fencing
GIMO: Gaze-Informed Human Motion Prediction in Context
ActAR: Actor-Driven Pose Embeddings for Video Action Recognition
Learning Compositional Representations for Effective Low-Shot Generalization
ParkPredict+: Multimodal Intent and Motion Prediction for Vehicles in Parking Lots with CNN and Transformer
Invisible-to-Visible: Privacy-Aware Human Instance Segmentation using Airborne Ultrasound via Collaborative Learning Variational Autoencoder
An Identity-Preserved Framework for Human Motion Transfer
No Token Left Behind: Explainability-Aided Image Classification and Generation
Robust Cross-Modal Representation Learning with Progressive Self-Distillation
E^2TAD: An Energy-Efficient Tracking-based Action Detector
Frequency Selective Augmentation for Video Representation Learning
Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
Unified Contrastive Learning in Image-Text-Label Space
TorMentor: Deterministic dynamic-path, data augmentations with fractals
MM-SEAL: A Large-scale Video Dataset of Multi-person Multi-grained Spatio-temporally Action Localization
An Empirical Study of End-to-End Temporal Action Detection
Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models
Attribute Prototype Network for Any-Shot Learning
An Analysis of Semantically-Aligned Speech-Text Embeddings
Direct Dense Pose Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.