30 citations · 51 across the 11 of their papers we have counts for
11 papers
Two-level Graph Network for Few-Shot Class-Incremental Learning
Hao Chen, Linyan Li, Fan Lyu +3
Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge…
Centroid Distance Distillation for Effective Rehearsal in Continual Learning
Daofeng Liu, Fan Lyu, Linyan Li +2
Rehearsal, retraining on a stored small data subset of old tasks, has been proven effective in solving catastrophic forgetting in continual learning. However, due to the sampled da…
Multi-Label Continual Learning using Augmented Graph Convolutional Network
Kaile Du, Fan Lyu, Linyan Li +5
Multi-Label Continual Learning (MLCL) builds a class-incremental framework in a sequential multi-label image recognition data stream. The critical challenges of MLCL are the constr…
Class-Incremental Lifelong Learning in Multi-Label Classification
Kaile Du, Linyan Li, Fan Lyu +3
Existing class-incremental lifelong learning studies only the data is with single-label, which limits its adaptation to multi-label data. This paper studies Lifelong Multi-Label (L…
AGCN: Augmented Graph Convolutional Network for Lifelong Multi-label Image Recognition
Kaile Du, Fan Lyu, Fuyuan Hu +4
The Lifelong Multi-Label (LML) image recognition builds an online class-incremental classifier in a sequential multi-label image recognition data stream. The key challenges of LML…
Each Attribute Matters: Contrastive Attention for Sentence-based Image Editing
Liuqing Zhao, Fan Lyu, Fuyuan Hu +3
Sentence-based Image Editing (SIE) aims to deploy natural language to edit an image. Offering potentials to reduce expensive manual editing, SIE has attracted much interest recentl…
Disentangling Semantic-to-visual Confusion for Zero-shot Learning
Zihan Ye, Fuyuan Hu, Fan Lyu +2
Using generative models to synthesize visual features from semantic distribution is one of the most popular solutions to ZSL image classification in recent years. The triplet loss…
Coarse to Fine: Multi-label Image Classification with Global/Local Attention
Fan Lyu, Fuyuan Hu, Victor S. Sheng +3
In our daily life, the scenes around us are always with multiple labels especially in a smart city, i.e., recognizing the information of city operation to response and control. Gre…
Multi-Domain Multi-Task Rehearsal for Lifelong Learning
Fan Lyu, Shuai Wang, Wei Feng +3
Rehearsal, seeking to remind the model by storing old knowledge in lifelong learning, is one of the most effective ways to mitigate catastrophic forgetting, i.e., biased forgetting…
Associating Multi-Scale Receptive Fields for Fine-grained Recognition
Zihan Ye, Fuyuan Hu, Yin Liu +3
Extracting and fusing part features have become the key of fined-grained image recognition. Recently, Non-local (NL) module has shown excellent improvement in image recognition. Ho…
SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning
Zihan Ye, Fan Lyu, Linyan Li +3
The existing Zero-Shot learning (ZSL) methods may suffer from the vague class attributes that are highly overlapped for different classes. Unlike these methods that ignore the disc…