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.
CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
CAARMA: Class Augmentation with Adversarial Mixup Regularization
Semantic Segmentation of Transparent and Opaque Drinking Glasses with the Help of Zero-shot Learning
LEGION: Learning to Ground and Explain for Synthetic Image Detection
Towards Achieving Perfect Multimodal Alignment
Sparseformer: a Transferable Transformer with Multi-granularity Token Sparsification for Medical Time Series Classification
Leveraging MoE-based Large Language Model for Zero-Shot Multi-Task Semantic Communication
Persistent Homology-induced Graph Ensembles for Time Series Regressions
Advancing Medical Representation Learning Through High-Quality Data
Bayesian Modeling of Zero-Shot Classifications for Urban Flood Detection
Real-Time Cell Sorting with Scalable In Situ FPGA-Accelerated Deep Learning
TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification
Zero-TIG: Temporal Consistency-Aware Zero-Shot Illumination-Guided Low-light Video Enhancement
An experimental approach on Few Shot Class Incremental Learning
Systematic Classification of Studies Investigating Social Media Conversations about Long COVID Using a Novel Zero-Shot Transformer Framework
MoFlow: One-Step Flow Matching for Human Trajectory Forecasting via Implicit Maximum Likelihood Estimation based Distillation
SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning
Leveraging Vision-Language Embeddings for Zero-Shot Learning in Histopathology Images
Trajectory Mamba: Efficient Attention-Mamba Forecasting Model Based on Selective SSM
ChatGPT Encounters Morphing Attack Detection: Zero-Shot MAD with Multi-Modal Large Language Models and General Vision Models
Natural Humanoid Robot Locomotion with Generative Motion Prior
Have LLMs Made Active Learning Obsolete? Surveying the NLP Community
Investigating the Effectiveness of a Socratic Chain-of-Thoughts Reasoning Method for Task Planning in Robotics, A Case Study
Controlling Latent Diffusion Using Latent CLIP
BiasEdit: Debiasing Stereotyped Language Models via Model Editing
Lend a Hand: Semi Training-Free Cued Speech Recognition via MLLM-Driven Hand Modeling for Barrier-free Communication
MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classification
Generative AI in Transportation Planning: A Survey
A Zero-shot Learning Method Based on Large Language Models for Multi-modal Knowledge Graph Embedding
LEGO-Motion: Learning-Enhanced Grids with Occupancy Instance Modeling for Class-Agnostic Motion Prediction
SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic
TimeLoc: A Unified End-to-End Framework for Precise Timestamp Localization in Long Videos
DiffCLIP: Differential Attention Meets CLIP
A Novel Distributed PV Power Forecasting Approach Based on Time-LLM
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.