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.
GIPCOL: Graph-Injected Soft Prompting for Compositional Zero-Shot Learning
Massive Editing for Large Language Models via Meta Learning
Social Motion Prediction with Cognitive Hierarchies
Analysis and Applications of Deep Learning with Finite Samples in Full Life-Cycle Intelligence of Nuclear Power Generation
Generalized zero-shot audio-to-intent classification
FPGA-QHAR: Throughput-Optimized for Quantized Human Action Recognition on The Edge
Leveraging Large-Scale Pretrained Vision Foundation Models for Label-Efficient 3D Point Cloud Segmentation
Distilling Knowledge from CNN-Transformer Models for Enhanced Human Action Recognition
Re-Scoring Using Image-Language Similarity for Few-Shot Object Detection
CLIP-AD: A Language-Guided Staged Dual-Path Model for Zero-shot Anomaly Detection
DEPN: Detecting and Editing Privacy Neurons in Pretrained Language Models
Pose-to-Motion: Cross-Domain Motion Retargeting with Pose Prior
Class Incremental Learning with Pre-trained Vision-Language Models
Large Trajectory Models are Scalable Motion Predictors and Planners
A Survey on Knowledge Editing of Neural Networks
AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection
Using Large Language Models to Support Thematic Analysis in Empirical Legal Studies
ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models
Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow
Distribution of Action Movements (DAM): A Descriptor for Human Action Recognition
6-DoF Stability Field via Diffusion Models
XFEVER: Exploring Fact Verification across Languages
Is ChatGPT a Good Multi-Party Conversation Solver?
EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition
Zephyr: Direct Distillation of LM Alignment
Knowledge Editing for Large Language Models: A Survey
Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization
Orientation-Aware Leg Movement Learning for Action-Driven Human Motion Prediction
Linear Representations of Sentiment in Large Language Models
Videoprompter: an ensemble of foundational models for zero-shot video understanding
Customising General Large Language Models for Specialised Emotion Recognition Tasks
NERetrieve: Dataset for Next Generation Named Entity Recognition and Retrieval
Is Weakly-supervised Action Segmentation Ready For Human-Robot Interaction? No, Let's Improve It With Action-union Learning
Equivariant Map and Agent Geometry for Autonomous Driving Motion Prediction
Robust NOMA-assisted OTFS-ISAC Network Design with 3D Motion Prediction Topology
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.