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.
Data-Driven Fairness Generalization for Deepfake Detection
Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees
Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification
Hierarchical Temporal Convolution Network:Towards Privacy-Centric Activity Recognition
DINOv2 Meets Text: A Unified Framework for Image- and Pixel-Level Vision-Language Alignment
Synchronized and Fine-Grained Head for Skeleton-Based Ambiguous Action Recognition
Adaptive Pruning for Large Language Models with Structural Importance Awareness
Human-Humanoid Robots Cross-Embodiment Behavior-Skill Transfer Using Decomposed Adversarial Learning from Demonstration
Counterexample Guided Program Repair Using Zero-Shot Learning and MaxSAT-based Fault Localization
MSA-GCN: Exploiting Multi-Scale Temporal Dynamics With Adaptive Graph Convolution for Skeleton-Based Action Recognition
Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question Answering
Real Classification by Description: Extending CLIP's Limits of Part Attributes Recognition
Joint Perception and Prediction for Autonomous Driving: A Survey
Learning from Massive Human Videos for Universal Humanoid Pose Control
Zero-Shot Image Moderation in Google Ads with LLM-Assisted Textual Descriptions and Cross-modal Co-embeddings
A Simple and Efficient Baseline for Zero-Shot Generative Classification
CRoF: CLIP-based Robust Few-shot Learning on Noisy Labels
ComprehendEdit: A Comprehensive Dataset and Evaluation Framework for Multimodal Knowledge Editing
Future Aspects in Human Action Recognition: Exploring Emerging Techniques and Ethical Influences
Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO
Concept-ROT: Poisoning Concepts in Large Language Models with Model Editing
ConceptEdit: Conceptualization-Augmented Knowledge Editing in Large Language Models for Commonsense Reasoning
Multi-Scale Incremental Modeling for Enhanced Human Motion Prediction in Human-Robot Collaboration
Discrepancy-Aware Attention Network for Enhanced Audio-Visual Zero-Shot Learning
Advancing Comprehensive Aesthetic Insight with Multi-Scale Text-Guided Self-Supervised Learning
An Efficient Framework for Enhancing Discriminative Models via Diffusion Techniques
Temporal Action Localization with Cross Layer Task Decoupling and Refinement
USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation
Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?
Model-Editing-Based Jailbreak against Safety-aligned Large Language Models
Zero-Shot Mono-to-Binaural Speech Synthesis
Assessing Personalized AI Mentoring with Large Language Models in the Computing Field
SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting
GPD-1: Generative Pre-training for Driving
Retaining and Enhancing Pre-trained Knowledge in Vision-Language Models with Prompt Ensembling
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.