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.
MotionWavelet: Human Motion Prediction via Wavelet Manifold Learning
OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions
TableTime: Reformulating Time Series Classification as Zero-Shot Table Understanding via Large Language Models
ChatBCI: A P300 Speller BCI Leveraging Large Language Models for Improved Sentence Composition in Realistic Scenarios
Lifelong Knowledge Editing for Vision Language Models with Low-Rank Mixture-of-Experts
Adaptive Hyper-Graph Convolution Network for Skeleton-based Human Action Recognition with Virtual Connections
When Spatial meets Temporal in Action Recognition
CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation
Safety Without Semantic Disruptions: Editing-free Safe Image Generation via Context-preserving Dual Latent Reconstruction
DriveMLLM: A Benchmark for Spatial Understanding with Multimodal Large Language Models in Autonomous Driving
Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition
Visual-Oriented Fine-Grained Knowledge Editing for MultiModal Large Language Models
Efficient Transfer Learning for Video-language Foundation Models
Visual-Semantic Graph Matching Net for Zero-Shot Learning
Leveraging MLLM Embeddings and Attribute Smoothing for Compositional Zero-Shot Learning
ModeSeq: Taming Sparse Multimodal Motion Prediction with Sequential Mode Modeling
TDSM: Triplet Diffusion for Skeleton-Text Matching in Zero-Shot Action Recognition
CorrCLIP: Reconstructing Correlations in CLIP with Off-the-Shelf Foundation Models for Open-Vocabulary Semantic Segmentation
DiVR: incorporating context from diverse VR scenes for human trajectory prediction
Can MLLMs Guide Weakly-Supervised Temporal Action Localization Tasks?
Measuring similarity between embedding spaces using induced neighborhood graphs
Model Editing for LLMs4Code: How Far are We?
NatureLM-audio: an Audio-Language Foundation Model for Bioacoustics
Extended multi-stream temporal-attention module for skeleton-based human action recognition (HAR)
ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving
Enhancing Visual Classification using Comparative Descriptors
Asterisk*: Keep it Simple
Emotional Images: Assessing Emotions in Images and Potential Biases in Generative Models
Relation Learning and Aggregate-attention for Multi-person Motion Prediction
RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
UnityGraph: Unified Learning of Spatio-temporal features for Multi-person Motion Prediction
A Mamba Foundation Model for Time Series Forecasting
ARN-LSTM: A Multi-Stream Fusion Model for Skeleton-based Action Recognition
Learning Where to Edit Vision Transformers
Advancing Cyber-Attack Detection in Power Systems: A Comparative Study of Machine Learning and Graph Neural Network Approaches
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.