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.
Multi-level Cross-modal Feature Alignment via Contrastive Learning towards Zero-shot Classification of Remote Sensing Image Scenes
High-Performance Inference Graph Convolutional Networks for Skeleton-Based Action Recognition
Proposal-Based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization
Fourier Analysis on Robustness of Graph Convolutional Neural Networks for Skeleton-based Action Recognition
Learning Conditional Attributes for Compositional Zero-Shot Learning
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
Improved Probabilistic Image-Text Representations
Explicit Visual Prompting for Universal Foreground Segmentations
FMM-X3D: FPGA-based modeling and mapping of X3D for Human Action Recognition
Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy
Adapting Language-Audio Models as Few-Shot Audio Learners
GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
Detecting Edit Failures In Large Language Models: An Improved Specificity Benchmark
CAILA: Concept-Aware Intra-Layer Adapters for Compositional Zero-Shot Learning
Deep Neural Networks in Video Human Action Recognition: A Review
Action Sensitivity Learning for Temporal Action Localization
Multilingual Text-to-Speech Synthesis for Turkic Languages Using Transliteration
DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification
EXnet: Efficient In-context Learning for Data-less Text classification
MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions
Universal Self-Adaptive Prompting
Editing Common Sense in Transformers
OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning
LAraBench: Benchmarking Arabic AI with Large Language Models
High Speed Human Action Recognition using a Photonic Reservoir Computer
Editable Graph Neural Network for Node Classifications
Perception Test: A Diagnostic Benchmark for Multimodal Video Models
Parts of Speech-Grounded Subspaces in Vision-Language Models
S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions
Navigating Prompt Complexity for Zero-Shot Classification: A Study of Large Language Models in Computational Social Science
Prompting Language-Informed Distribution for Compositional Zero-Shot Learning
Are Large Language Models Robust Coreference Resolvers?
Can We Edit Factual Knowledge by In-Context Learning?
Spatiotemporal Attention-based Semantic Compression for Real-time Video Recognition
Editing Large Language Models: Problems, Methods, and Opportunities
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.