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.
Model editing for distribution shifts in uranium oxide morphological analysis
Semi-Supervised Pipe Video Temporal Defect Interval Localization
Rethinking Domain Adaptation and Generalization in the Era of CLIP
Multi-modal Relation Distillation for Unified 3D Representation Learning
Zero-Shot Underwater Gesture Recognition
ESP-MedSAM: Efficient Self-Prompting SAM for Universal Domain-Generalized Medical Image Segmentation
LORTSAR: Low-Rank Transformer for Skeleton-based Action Recognition
Towards a "universal translator" for neural dynamics at single-cell, single-spike resolution
Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism
Audio-visual Generalized Zero-shot Learning the Easy Way
SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders
Attention Based Simple Primitives for Open World Compositional Zero-Shot Learning
An Application of Large Language Models to Coding Negotiation Transcripts
Compound Expression Recognition via Multi Model Ensemble for the ABAW7 Challenge
Shap-Mix: Shapley Value Guided Mixing for Long-Tailed Skeleton Based Action Recognition
ModalChorus: Visual Probing and Alignment of Multi-modal Embeddings via Modal Fusion Map
Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer
ActionSwitch: Class-agnostic Detection of Simultaneous Actions in Streaming Videos
InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains
Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction
CATD: Unified Representation Learning for EEG-to-fMRI Cross-Modal Generation
Anticipating Future Object Compositions without Forgetting
Codebook LLMs: Evaluating LLMs as Measurement Tools for Political Science Concepts
STARS: Self-supervised Tuning for 3D Action Recognition in Skeleton Sequences
Do You Act Like You Talk? Exploring Pose-based Driver Action Classification with Speech Recognition Networks
Augmented Neural Fine-Tuning for Efficient Backdoor Purification
Cross-Lingual Multi-Hop Knowledge Editing -- Benchmarks, Analysis and a Simple Contrastive Learning based Approach
Dense Multimodal Alignment for Open-Vocabulary 3D Scene Understanding
ScaleFlow++: Robust and Accurate Estimation of 3D Motion from Video
PFPs: Prompt-guided Flexible Pathological Segmentation for Diverse Potential Outcomes Using Large Vision and Language Models
Full-Stage Pseudo Label Quality Enhancement for Weakly-supervised Temporal Action Localization
STD-PLM: Understanding Both Spatial and Temporal Properties of Spatial-Temporal Data with PLM
Adaptive Prediction Ensemble: Improving Out-of-Distribution Generalization of Motion Forecasting
Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning
Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.