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.
A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications
Prefix Conditioning Unifies Language and Label Supervision
Learning Invariant Visual Representations for Compositional Zero-Shot Learning
Post-hoc Concept Bottleneck Models
Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction
Skeleton-based Action Recognition via Temporal-Channel Aggregation
Prompt Injection: Parameterization of Fixed Inputs
CyCLIP: Cyclic Contrastive Language-Image Pretraining
PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences
2D versus 3D Convolutional Spiking Neural Networks Trained with Unsupervised STDP for Human Action Recognition
MMNet: A Model-Based Multimodal Network for Human Action Recognition in RGB-D Videos
Language Anisotropic Cross-Lingual Model Editing
Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning
Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes
Exploring Map-based Features for Efficient Attention-based Vehicle Motion Prediction
GraSens: A Gabor Residual Anti-aliasing Sensing Framework for Action Recognition using WiFi
Learning to Model Editing Processes
Structured Attention Composition for Temporal Action Localization
Sliding-Window Normalization to Improve the Performance of Machine-Learning Models for Real-Time Motion Prediction Using Electromyography
PYSKL: Towards Good Practices for Skeleton Action Recognition
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving
Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generator
Disentangling Visual Embeddings for Attributes and Objects
KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning
Open Vocabulary Extreme Classification Using Generative Models
Learning to Answer Visual Questions from Web Videos
Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement
Goal-Oriented Next Best Activity Recommendation using Reinforcement Learning
Handcrafted localized phase features for human action recognition
BasicTAD: an Astounding RGB-Only Baseline for Temporal Action Detection
ANUBIS: Skeleton Action Recognition Dataset, Review, and Benchmark
Detection Recovery in Online Multi-Object Tracking with Sparse Graph Tracker
D-DPCC: Deep Dynamic Point Cloud Compression via 3D Motion Prediction
Convex Combination Consistency between Neighbors for Weakly-supervised Action Localization
Improving Model Performance and Removing the Class Imbalance Problem Using Augmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.