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.
Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning
Self-Supervised Approach to Addressing Zero-Shot Learning Problem
Debiased Learning from Naturally Imbalanced Pseudo-Labels
Learning Semantic Ambiguities for Zero-Shot Learning
ZeroBERTo: Leveraging Zero-Shot Text Classification by Topic Modeling
Semantically Grounded Visual Embeddings for Zero-Shot Learning
A Neural Network Solves, Explains, and Generates University Math Problems by Program Synthesis and Few-Shot Learning at Human Level
Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction
Semantic Feature Extraction for Generalized Zero-shot Learning
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model
A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision
Learning Aligned Cross-Modal Representation for Generalized Zero-Shot Classification
Domain-Aware Continual Zero-Shot Learning
Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation
3D Skeleton-based Few-shot Action Recognition with JEANIE is not so Naïve
ACGNet: Action Complement Graph Network for Weakly-supervised Temporal Action Localization
Dynamic Hypergraph Convolutional Networks for Skeleton-Based Action Recognition
Few-shot Learning with Multilingual Language Models
Precondition and Effect Reasoning for Action Recognition
MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks
Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Survey
Self-attention based anchor proposal for skeleton-based action recognition
Data Efficient Language-supervised Zero-shot Recognition with Optimal Transport Distillation
Analysis and Evaluation of Kinect-based Action Recognition Algorithms
TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning
Extreme Zero-Shot Learning for Extreme Text Classification
MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection
A Heterogeneous Graph Learning Model for Cyber-Attack Detection
Decoupling Zero-Shot Semantic Segmentation
Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks
Temporal Action Proposal Generation with Background Constraint
Estimating Uncertainty For Vehicle Motion Prediction on Yandex Shifts Dataset
CLIP-Lite: Information Efficient Visual Representation Learning with Language Supervision
Temporal Transformer Networks with Self-Supervision for Action Recognition
Deep Hierarchical Representation of Point Cloud Videos via Spatio-Temporal Decomposition
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.