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.
Zero-Shot Classification by Logical Reasoning on Natural Language Explanations
Predicting User-specific Future Activities using LSTM-based Multi-label Classification
MSMG-Net: Multi-scale Multi-grained Supervised Metworks for Multi-task Image Manipulation Detection and Localization
Simple Primitives with Feasibility- and Contextuality-Dependence for Open-World Compositional Zero-shot Learning
P4P: Conflict-Aware Motion Prediction for Planning in Autonomous Driving
An Empirical Bayes Analysis of Object Trajectory Representation Models
Crosslingual Generalization through Multitask Finetuning
Could Giant Pretrained Image Models Extract Universal Representations?
An Information-Theoretic Approach for Estimating Scenario Generalization in Crowd Motion Prediction
Fine-grained Visual-Text Prompt-Driven Self-Training for Open-Vocabulary Object Detection
Deep Learning Computer Vision Algorithms for Real-time UAVs On-board Camera Image Processing
Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese
Temporal-Viewpoint Transportation Plan for Skeletal Few-shot Action Recognition
End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator
Beyond Prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations
Being Comes from Not-being: Open-vocabulary Text-to-Motion Generation with Wordless Training
Towards trustworthy multi-modal motion prediction: Holistic evaluation and interpretability of outputs
Text2Model: Text-based Model Induction for Zero-shot Image Classification
Handwashing Action Detection System for an Autonomous Social Robot
Towards Reliable Zero Shot Classification in Self-Supervised Models with Conformal Prediction
Zero-Shot Learning of a Conditional Generative Adversarial Network for Data-Free Network Quantization
Don't Prompt, Search! Mining-based Zero-Shot Learning with Language Models
Holistic Interaction Transformer Network for Action Detection
TAPE: Assessing Few-shot Russian Language Understanding
ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback
PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points
General Image Descriptors for Open World Image Retrieval using ViT CLIP
Learning Attention Propagation for Compositional Zero-Shot Learning
TabLLM: Few-shot Classification of Tabular Data with Large Language Models
Multi-view Tracking Using Weakly Supervised Human Motion Prediction
Meta-Learning via Classifier(-free) Diffusion Guidance
Improving Object-centric Learning with Query Optimization
Non-Contrastive Learning Meets Language-Image Pre-Training
LAION-5B: An open large-scale dataset for training next generation image-text models
Towards Effective Image Manipulation Detection with Proposal Contrastive Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.