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.
MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding
It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap
Perturbation-Restrained Sequential Model Editing
TEII: Think, Explain, Interact and Iterate with Large Language Models to Solve Cross-lingual Emotion Detection
Controllable Longer Image Animation with Diffusion Models
CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale
Listenable Maps for Zero-Shot Audio Classifiers
DarijaBanking: A New Resource for Overcoming Language Barriers in Banking Intent Detection for Moroccan Arabic Speakers
CapS-Adapter: Caption-based MultiModal Adapter in Zero-Shot Classification
Large Scale Knowledge Washing
CLIP model is an Efficient Online Lifelong Learner
Off-the-shelf ChatGPT is a Good Few-shot Human Motion Predictor
BDetCLIP: Multimodal Prompting Contrastive Test-Time Backdoor Detection
Everything is Editable: Extend Knowledge Editing to Unstructured Data in Large Language Models
Leveraging Logical Rules in Knowledge Editing: A Cherry on the Top
Benchmarking the Performance of Pre-trained LLMs across Urdu NLP Tasks
What Do You See? Enhancing Zero-Shot Image Classification with Multimodal Large Language Models
Chain-of-Thought Prompting for Demographic Inference with Large Multimodal Models
Harmony: A Joint Self-Supervised and Weakly-Supervised Framework for Learning General Purpose Visual Representations
Tuning-free Universally-Supervised Semantic Segmentation
MAMBA4D: Efficient Long-Sequence Point Cloud Video Understanding with Disentangled Spatial-Temporal State Space Models
Enhanced Spatiotemporal Prediction Using Physical-guided And Frequency-enhanced Recurrent Neural Networks
Implicit In-context Learning
Extreme Solar Flare Prediction Using Residual Networks with HMI Magnetograms and Intensitygrams
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
Magnetic Resonance Image Processing Transformer for General Accelerated Image Reconstruction
Floor-Plan-aided Indoor Localization: Zero-Shot Learning Framework, Data Sets, and Prototype
Counterfactual Gradients-based Quantification of Prediction Trust in Neural Networks
Unleashing the Power of Unlabeled Data: A Self-supervised Learning Framework for Cyber Attack Detection in Smart Grids
Model Editing as a Robust and Denoised variant of DPO: A Case Study on Toxicity
From CNNs to Transformers in Multimodal Human Action Recognition: A Survey
Evaluating and Modeling Social Intelligence: A Comparative Study of Human and AI Capabilities
Decoding by Contrasting Knowledge: Enhancing LLMs' Confidence on Edited Facts
LiPost: Improved Content Understanding With Effective Use of Multi-task Contrastive Learning
Towards Consistent and Explainable Motion Prediction using Heterogeneous Graph Attention
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.