Incremental zero-shot learning

K Wei, C Deng, X Yang, D Tao - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
The goal of zero-shot learning (ZSL) is to recognize objects from unseen classes correctly
without corresponding training samples. The existing ZSL methods are trained on a set of …

Km4: Visual reasoning via knowledge embedding memory model with mutual modulation

W Zheng, L Yan, C Gou, FY Wang - Information Fusion, 2021 - Elsevier
Visual reasoning is a special kind of visual question answering, which is essentially multi-
step and compositional, and also requires intensive text-visual interaction. The most …

What can covid-19 teach us about using ai in pandemics?

K Laudanski, G Shea, M DiMeglio, M Restrepo… - Healthcare, 2020 - mdpi.com
The COVID-19 pandemic put significant strain on societies and their resources, with the
healthcare system and workers being particularly affected. Artificial Intelligence (AI) offers …

Scellseg: A style-aware deep learning tool for adaptive cell instance segmentation by contrastive fine-tuning

D Xun, D Chen, Y Zhou, VM Lauschke, R Wang… - IScience, 2022 - cell.com
Deep learning-based cell segmentation is increasingly utilized in cell biology due to the
massive accumulation of large-scale datasets and excellent progress in model architecture …

An end-to-end deep generative approach with meta-learning optimization for zero-shot object classification

X Xu, X Bao, X Lu, R Zhang, X Chen, G Lu - Information Processing & …, 2023 - Elsevier
Zero-shot object classification aims to recognize the object of unseen classes whose
supervised data are unavailable in the training stage. Recent zero-shot learning (ZSL) …

Automatic RFI identification for Sentinel-1 based on Siamese-type deep CNN using repeat-pass images

X Lu, C Wang, X Xu, H Yang, S Zhang… - … on Geoscience and …, 2022 - ieeexplore.ieee.org
Since the start of the Sentinel-1 (S-1) mission, numerous cases of severe image degradation
caused by radio frequency interference (RFI) have been reported, which puts forward an …

Semantic enhanced knowledge graph for large-scale zero-shot learning

J Wei, Y Yang, Z Ma, J Li, X Xu, HT Shen - arXiv preprint arXiv:2212.13151, 2022 - arxiv.org
Zero-Shot Learning has been a highlighted research topic in both vision and language
areas. Recently, most existing methods adopt structured knowledge information to model …

Cross-layer autoencoder for zero-shot learning

Z Zhang, Y Li, J Yang, Y Li, M Gao - IEEE Access, 2019 - ieeexplore.ieee.org
Zero-shot learning (ZSL) is the task of recognizing samples from their related classes which
have never been seen during model training. ZSL is generally realized through learning a …

MetaMove: On improving human mobility classification and prediction via metalearning

F Zhou, X Liu, T Zhong… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Despite offering efficient solutions to a plethora of novel challenges, existing approaches on
mobility modeling require a large amount of labeled data when training effective and …

Cooperative coupled generative networks for generalized zero-shot learning

L Sun, J Song, Y Wang, B Li - IEEE Access, 2020 - ieeexplore.ieee.org
Compared with zero-shot learning (ZSL), the generalized zero-shot learning (GZSL) is more
challenging since its test samples are taken from both seen and unseen classes. Most …