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.
Learning to Predict Diverse Human Motions from a Single Image via Mixture Density Networks
Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media
Adversarial Bone Length Attack on Action Recognition
Learning from Language Description: Low-shot Named Entity Recognition via Decomposed Framework
A Recipe For Arbitrary Text Style Transfer with Large Language Models
Hierarchical Graph Convolutional Skeleton Transformer for Action Recognition
CovarianceNet: Conditional Generative Model for Correct Covariance Prediction in Human Motion Prediction
Improving Phenotype Prediction using Long-Range Spatio-Temporal Dynamics of Functional Connectivity
Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP
Safety-aware Motion Prediction with Unseen Vehicles for Autonomous Driving
Finetuned Language Models Are Zero-Shot Learners
Multi-Modal Zero-Shot Sign Language Recognition
Conditional Extreme Value Theory for Open Set Video Domain Adaptation
Learning JPEG Compression Artifacts for Image Manipulation Detection and Localization
SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation
Multiscale Spatio-Temporal Graph Neural Networks for 3D Skeleton-Based Motion Prediction
Joint Learning Architecture for Multiple Object Tracking and Trajectory Forecasting
Field-Guide-Inspired Zero-Shot Learning
Online Dictionary Learning Based Fault and Cyber Attack Detection for Power Systems
TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment
DenseTNT: End-to-end Trajectory Prediction from Dense Goal Sets
Discriminative Region-based Multi-Label Zero-Shot Learning
MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition
Generating Smooth Pose Sequences for Diverse Human Motion Prediction
Self-Supervised Video Representation Learning with Meta-Contrastive Network
Contrastive Language-Image Pre-training for the Italian Language
Stochastic Scene-Aware Motion Prediction
The Multi-Modal Video Reasoning and Analyzing Competition
Structure-Aware Feature Generation for Zero-Shot Learning
MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction
Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation
Towards Visual Explainable Active Learning for Zero-Shot Classification
Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization
Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds
MeetSum: Transforming Meeting Transcript Summarization using Transformers!
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.