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 Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worlds
Deep Ensemble Learning with Frame Skipping for Face Anti-Spoofing
Distilling Large Vision-Language Model with Out-of-Distribution Generalizability
NMS Threshold matters for Ego4D Moment Queries -- 2nd place solution to the Ego4D Moment Queries Challenge 2023
Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Data
Physics-based Motion Retargeting from Sparse Inputs
SpATr: MoCap 3D Human Action Recognition based on Spiral Auto-encoder and Transformer Network
Miniaturized Graph Convolutional Networks with Topologically Consistent Pruning
MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying
Stay on topic with Classifier-Free Guidance
Qualitative Prediction of Multi-Agent Spatial Interactions
The Segment Anything Model (SAM) for Remote Sensing Applications: From Zero to One Shot
End-to-end Autonomous Driving: Challenges and Frontiers
The mapKurator System: A Complete Pipeline for Extracting and Linking Text from Historical Maps
Towards Open Vocabulary Learning: A Survey
Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity
Is ChatGPT a Biomedical Expert? -- Exploring the Zero-Shot Performance of Current GPT Models in Biomedical Tasks
Theater Aid System for the Visually Impaired Through Transfer Learning of Spatio-Temporal Graph Convolution Networks
Multi-Dimensional Refinement Graph Convolutional Network with Robust Decouple Loss for Fine-Grained Skeleton-Based Action Recognition
An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning
MotionGPT: Human Motion as a Foreign Language
SIMMF: Semantics-aware Interactive Multiagent Motion Forecasting for Autonomous Vehicle Driving
Learning Scene Flow With Skeleton Guidance For 3D Action Recognition
The MI-Motion Dataset and Benchmark for 3D Multi-Person Motion Prediction
Temporal Action Proposal Generation With Action Frequency Adaptive Network
RXFOOD: Plug-in RGB-X Fusion for Object of Interest Detection
"Filling the Blanks'': Identifying Micro-activities that Compose Complex Human Activities of Daily Living
Physics-constrained Attack against Convolution-based Human Motion Prediction
RS5M and GeoRSCLIP: A Large Scale Vision-Language Dataset and A Large Vision-Language Model for Remote Sensing
Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition
Collision Avoidance Detour for Multi-Agent Trajectory Forecasting
Multiverse Transformer: 1st Place Solution for Waymo Open Sim Agents Challenge 2023
Frame Fusion with Vehicle Motion Prediction for 3D Object Detection
PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird's-Eye View
RedMotion: Motion Prediction via Redundancy Reduction
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.