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.
Identifying Knowledge Editing Types in Large Language Models
From Unimodal to Multimodal: Scaling up Projectors to Align Modalities
"Why" Has the Least Side Effect on Model Editing
S2O: Static to Openable Enhancement for Articulated 3D Objects
NeuroPath: A Neural Pathway Transformer for Joining the Dots of Human Connectomes
CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
CASPFormer: Trajectory Prediction from BEV Images with Deformable Attention
Pioneering Reliable Assessment in Text-to-Image Knowledge Editing: Leveraging a Fine-Grained Dataset and an Innovative Criterion
Perturb, Attend, Detect and Localize (PADL): Robust Proactive Image Defense
Spatial Hierarchy and Temporal Attention Guided Cross Masking for Self-supervised Skeleton-based Action Recognition
Pruning Multilingual Large Language Models for Multilingual Inference
Data-efficient Trajectory Prediction via Coreset Selection
Zero-shot forecasting of chaotic systems
Efficient Motion Prediction: A Lightweight & Accurate Trajectory Prediction Model With Fast Training and Inference Speed
Task-oriented Prompt Enhancement via Script Generation
An Effective Approach to Embedding Source Code by Combining Large Language and Sentence Embedding Models
Dumpling GNN: Hybrid GNN Enables Better ADC Payload Activity Prediction Based on Chemical Structure
For Overall Nighttime Visibility: Integrate Irregular Glow Removal With Glow-Aware Enhancement
Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
Zero-Shot Skeleton-based Action Recognition with Dual Visual-Text Alignment
Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis
Redefining Data Pairing for Motion Retargeting Leveraging a Human Body Prior
Deep learning for fast segmentation and critical dimension metrology & characterization enabling AR/VR design and fabrication
Bayesian-Optimized One-Step Diffusion Model with Knowledge Distillation for Real-Time 3D Human Motion Prediction
Enhancing Agricultural Environment Perception via Active Vision and Zero-Shot Learning
Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Space
Hypergraph-based Motion Generation with Multi-modal Interaction Relational Reasoning
MQA-KEAL: Multi-hop Question Answering under Knowledge Editing for Arabic Language
Annealed Winner-Takes-All for Motion Forecasting
StruEdit: Structured Outputs Enable the Fast and Accurate Knowledge Editing for Large Language Models
From Text to Emoji: How PEFT-Driven Personality Manipulation Unleashes the Emoji Potential in LLMs
ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video
Can Large Language Models Grasp Event Signals? Exploring Pure Zero-Shot Event-based Recognition
Benchmarking LLMs in Political Content Text-Annotation: Proof-of-Concept with Toxicity and Incivility Data
DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.