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.
Efficient Test-Time Prompt Tuning for Vision-Language Models
On zero-shot learning in neural state estimation of power distribution systems
EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition
ChatGPT Meets Iris Biometrics
Pedestrian Motion Prediction Using Transformer-based Behavior Clustering and Data-Driven Reachability Analysis
Online Temporal Action Localization with Memory-Augmented Transformer
LLM-based MOFs Synthesis Condition Extraction using Few-Shot Demonstrations
Do Large Language Models Speak All Languages Equally? A Comparative Study in Low-Resource Settings
Evaluating Vision-Language Models for Zero-Shot Detection, Classification, and Association of Motorcycles, Passengers, and Helmets
Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts
Geometric Algebra Meets Large Language Models: Instruction-Based Transformations of Separate Meshes in 3D, Interactive and Controllable Scenes
The Mechanics of Conceptual Interpretation in GPT Models: Interpretative Insights
AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosis
Enhancing Human Action Recognition and Violence Detection Through Deep Learning Audiovisual Fusion
Past Movements-Guided Motion Representation Learning for Human Motion Prediction
Signal-SGN: A Spiking Graph Convolutional Network for Skeletal Action Recognition via Learning Temporal-Frequency Dynamics
Out-Of-Distribution Detection for Audio-visual Generalized Zero-Shot Learning: A General Framework
Skeleton-Based Action Recognition with Spatial-Structural Graph Convolution
EZSR: Event-based Zero-Shot Recognition
Can LLMs be Fooled? Investigating Vulnerabilities in LLMs
Prompting Encoder Models for Zero-Shot Classification: A Cross-Domain Study in Italian
Leveraging Foundation Models for Zero-Shot IoT Sensing
Generative Diffusion Model Bootstraps Zero-shot Classification of Fetal Ultrasound Images In Underrepresented African Populations
Can Editing LLMs Inject Harm?
Forecast-PEFT: Parameter-Efficient Fine-Tuning for Pre-trained Motion Forecasting Models
Harmfully Manipulated Images Matter in Multimodal Misinformation Detection
ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Tasks
Adversarial Robustification via Text-to-Image Diffusion Models
I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition
Multi-label Cluster Discrimination for Visual Representation Learning
C3T: Cross-modal Transfer Through Time for Sensor-based Human Activity Recognition
Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Visual-Semantic Decomposition and Partial Alignment for Document-based Zero-Shot Learning
Flow-guided Motion Prediction with Semantics and Dynamic Occupancy Grid Maps
A Life-long Learning Intrusion Detection System for 6G-Enabled IoV
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.