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.
See the Unseen: Better Context-Consistent Knowledge-Editing by Noises
Exploiting GPT-4 Vision for Zero-shot Point Cloud Understanding
Foundation Models for Biomedical Image Segmentation: A Survey
3D Object Detection and High-Resolution Traffic Parameters Extraction Using Low-Resolution LiDAR Data
SamLP: A Customized Segment Anything Model for License Plate Detection
Batch-ICL: Effective, Efficient, and Order-Agnostic In-Context Learning
Modality-Aware Representation Learning for Zero-shot Sketch-based Image Retrieval
AdvMT: Adversarial Motion Transformer for Long-term Human Motion Prediction
CLIP-Guided Source-Free Object Detection in Aerial Images
Can Active Label Correction Improve LLM-based Modular AI Systems?
TwinBooster: Synergising Large Language Models with Barlow Twins and Gradient Boosting for Enhanced Molecular Property Prediction
Model Editing Harms General Abilities of Large Language Models: Regularization to the Rescue
Disentangled Neural Relational Inference for Interpretable Motion Prediction
MPN: Leveraging Multilingual Patch Neuron for Cross-lingual Model Editing
Benchmarking PathCLIP for Pathology Image Analysis
Zero-shot Microclimate Prediction with Deep Learning
Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes Interactively
Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions
Large Language Models Relearn Removed Concepts
Query-Based Knowledge Sharing for Open-Vocabulary Multi-Label Classification
A Comprehensive Study of Knowledge Editing for Large Language Models
Diffusion Models, Image Super-Resolution And Everything: A Survey
Skeleton2vec: A Self-supervised Learning Framework with Contextualized Target Representations for Skeleton Sequence
Pushing Boundaries: Exploring Zero Shot Object Classification with Large Multimodal Models
A Large-Scale Re-identification Analysis in Sporting Scenarios: the Betrayal of Reaching a Critical Point
FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models
AI Content Self-Detection for Transformer-based Large Language Models
Attention-aware Social Graph Transformer Networks for Stochastic Trajectory Prediction
Revealing the Proximate Long-Tail Distribution in Compositional Zero-Shot Learning
A Prompt Learning Framework for Source Code Summarization
Spatial-Temporal Decoupling Contrastive Learning for Skeleton-based Human Action Recognition
PokeMQA: Programmable knowledge editing for Multi-hop Question Answering
Do LLM Agents Exhibit Social Behavior?
Classifying Soccer Ball-on-Goal Position Through Kicker Shooting Action
On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.