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.
Similarity-Quantized Relative Difference Learning for Improved Molecular Activity Prediction
FLAVARS: A Multimodal Foundational Language and Vision Alignment Model for Remote Sensing
IoT-Based Real-Time Medical-Related Human Activity Recognition Using Skeletons and Multi-Stage Deep Learning for Healthcare
Duplex: Dual Prototype Learning for Compositional Zero-Shot Learning
BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature
Generate, Transduct, Adapt: Iterative Transduction with VLMs
Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
Improving Skeleton-based Action Recognition with Interactive Object Information
Explore Activation Sparsity in Recurrent LLMs for Energy-Efficient Neuromorphic Computing
Hidden Entity Detection from GitHub Leveraging Large Language Models
A Statistical Theory of Contrastive Pre-training and Multimodal Generative AI
Towards a scalable AI-driven framework for data-independent Cyber Threat Intelligence Information Extraction
Bridged Semantic Alignment for Zero-shot 3D Medical Image Diagnosis
Holistic Semantic Representation for Navigational Trajectory Generation
Gaussian Masked Autoencoders
Advanced Machine Learning Techniques for Social Support Detection on Social Media
Evolving Skeletons: Motion Dynamics in Action Recognition
A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges
LLMs & Legal Aid: Understanding Legal Needs Exhibited Through User Queries
Temporal Dynamics Decoupling with Inverse Processing for Enhancing Human Motion Prediction
Spatio-Temporal Multi-Subgraph GCN for 3D Human Motion Prediction
LLM-MedQA: Enhancing Medical Question Answering through Case Studies in Large Language Models
Knowledge Editing for Large Language Model with Knowledge Neuronal Ensemble
TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting
DAVE: Diverse Atomic Visual Elements Dataset with High Representation of Vulnerable Road Users in Complex and Unpredictable Environments
Generalized Uncertainty-Based Evidential Fusion with Hybrid Multi-Head Attention for Weak-Supervised Temporal Action Localization
Skeleton-based Action Recognition with Non-linear Dependency Modeling and Hilbert-Schmidt Independence Criterion
Improved Feature Generating Framework for Transductive Zero-shot Learning
Discriminative Image Generation with Diffusion Models for Zero-Shot Learning
Multiple Consistency-guided Test-Time Adaptation for Contrastive Audio-Language Models with Unlabeled Audio
DeepMF: Deep Motion Factorization for Closed-Loop Safety-Critical Driving Scenario Simulation
Knowledge Editing through Chain-of-Thought
Mimicking-Bench: A Benchmark for Generalizable Humanoid-Scene Interaction Learning via Human Mimicking
CARL-GT: Evaluating Causal Reasoning Capabilities of Large Language Models
Video Domain Incremental Learning for Human Action Recognition in Home Environments
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.