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.
Temporal Action Localization for Inertial-based Human Activity Recognition
ADM-Loc: Actionness Distribution Modeling for Point-supervised Temporal Action Localization
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models
ViT-Lens: Towards Omni-modal Representations
DUnE: Dataset for Unified Editing
Target-Free Compound Activity Prediction via Few-Shot Learning
IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective
tinyCLAP: Distilling Constrastive Language-Audio Pretrained Models
VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG
Dynamic Compositional Graph Convolutional Network for Efficient Composite Human Motion Prediction
Understanding the Vulnerability of CLIP to Image Compression
A New Benchmark and Model for Challenging Image Manipulation Detection
HOMOE: A Memory-Based and Composition-Aware Framework for Zero-Shot Learning with Hopfield Network and Soft Mixture of Experts
Compositional Zero-shot Learning via Progressive Language-based Observations
Attribute-Aware Representation Rectification for Generalized Zero-Shot Learning
Deep Learning and NLP in Cryptocurrency Forecasting: Integrating Financial, Blockchain, and Social Media Data
Self-guided Few-shot Semantic Segmentation for Remote Sensing Imagery Based on Large Vision Models
Boosting Audio-visual Zero-shot Learning with Large Language Models
Challenges in Video-Based Infant Action Recognition: A Critical Examination of the State of the Art
Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models
Continual Learning: Applications and the Road Forward
GeoSAM: Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation
Flexible Model Interpretability through Natural Language Model Editing
MAFALDA: A Benchmark and Comprehensive Study of Fallacy Detection and Classification
Assessing Knowledge Editing in Language Models via Relation Perspective
Investigating the Emergent Audio Classification Ability of ASR Foundation Models
Zero-Shot Segmentation of Eye Features Using the Segment Anything Model (SAM)
SkelVIT: Consensus of Vision Transformers for a Lightweight Skeleton-Based Action Recognition System
Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions
Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers
Unified machine learning tasks and datasets for enhancing renewable energy
CLAMP: A Contrastive Language And Molecule Pre-training Network
Trends in Integration of Knowledge and Large Language Models: A Survey and Taxonomy of Methods, Benchmarks, and Applications
Automatic Report Generation for Histopathology images using pre-trained Vision Transformers
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.