Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learning

1 code implementation • 31 Oct 2023 • Fuyuan Hu, Jian Zhang, Fan Lyu, Linyan Li, Fenglei Xu

Moreover, we design a multi-stage strategy for training S2C model, which mitigates the training challenges posed by limited data in the incremental process.

Few-Shot Class-Incremental Learning Graph Learning +1

Dynamic V2X Autonomous Perception from Road-to-Vehicle Vision

no code implementations • 29 Oct 2023 • Jiayao Tan, Fan Lyu, Linyan Li, Fuyuan Hu, Tingliang Feng, Fenglei Xu, Rui Yao

Vehicle-to-everything (V2X) perception is an innovative technology that enhances vehicle perception accuracy, thereby elevating the security and reliability of autonomous systems.

3D Object Detection object-detection

Two-level Graph Network for Few-Shot Class-Incremental Learning

no code implementations • 24 Mar 2023 • Hao Chen, Linyan Li, Fan Lyu, Fuyuan Hu, Zhenping Xia, Fenglei Xu

Class-level graph network aims to mitigate the semantic conflict between prototype features of new classes and old classes.

Few-Shot Class-Incremental Learning Incremental Learning +1

Centroid Distance Distillation for Effective Rehearsal in Continual Learning

1 code implementation • 6 Mar 2023 • Daofeng Liu, Fan Lyu, Linyan Li, Zhenping Xia, Fuyuan Hu

Rehearsal, retraining on a stored small data subset of old tasks, has been proven effective in solving catastrophic forgetting in continual learning.

Continual Learning

Multi-Label Continual Learning using Augmented Graph Convolutional Network

no code implementations • 27 Nov 2022 • Kaile Du, Fan Lyu, Linyan Li, Fuyuan Hu, Wei Feng, Fenglei Xu, Xuefeng Xi, Hanjing Cheng

In contrast, the inter-task relationships leverage hard and soft labels from data and a constructed expert network.

Continual Learning

Class-Incremental Lifelong Learning in Multi-Label Classification

1 code implementation • 16 Jul 2022 • Kaile Du, Linyan Li, Fan Lyu, Fuyuan Hu, Zhenping Xia, Fenglei Xu

This paper studies Lifelong Multi-Label (LML) classification, which builds an online class-incremental classifier in a sequential multi-label classification data stream.

Classification Multi-Label Classification

AGCN: Augmented Graph Convolutional Network for Lifelong Multi-label Image Recognition

1 code implementation • 10 Mar 2022 • Kaile Du, Fan Lyu, Fuyuan Hu, Linyan Li, Wei Feng, Fenglei Xu, Qiming Fu

The key challenges of LML image recognition are the construction of label relationships on Partial Labels of training data and the Catastrophic Forgetting on old classes, resulting in poor generalization.

Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing

1 code implementation • 21 Oct 2021 • Liuqing Zhao, Fan Lyu, Fuyuan Hu, Kaizhu Huang, Fenglei Xu, Linyan Li

Sentence-based Image Editing (SIE) aims to deploy natural language to edit an image.

Attribute Generative Adversarial Network +1

Disentangling Semantic-to-visual Confusion for Zero-shot Learning

1 code implementation • 16 Jun 2021 • Zihan Ye, Fuyuan Hu, Fan Lyu, Linyan Li, Kaizhu Huang

However, the traditional TL cannot search reliable unseen disentangled representations due to the unavailability of unseen classes in ZSL.

Generative Adversarial Network Image Classification +1

SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning

no code implementations • 15 Apr 2019 • Zihan Ye, Fan Lyu, Linyan Li, Qiming Fu, Jinchang Ren, Fuyuan Hu

First, we pre-train a Semantic Rectifying Network (SRN) to rectify semantic space with a semantic loss and a rectifying loss.

Generative Adversarial Network Zero-Shot Learning