no code implementations • 19 Mar 2024 • Kaile Du, Yifan Zhou, Fan Lyu, Yuyang Li, Chen Lu, Guangcan Liu
The partial label challenge in Multi-Label Class-Incremental Learning (MLCIL) arises when only the new classes are labeled during training, while past and future labels remain unavailable.
no code implementations • 13 Feb 2024 • Fan Lyu, Kaile Du, Yuyang Li, Hanyu Zhao, Zhang Zhang, Guangcan Liu, Liang Wang
At the source stage, we transform a pre-trained deterministic model into a Bayesian Neural Network (BNN) via a variational warm-up strategy, injecting uncertainties into the model.
no code implementations • 2 Jan 2024 • Fan Lyu, Wei Feng, Yuepan Li, Qing Sun, Fanhua Shang, Liang Wan, Liang Wang
The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks.
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.
no code implementations • 31 Oct 2023 • Weiqi Li, Fan Lyu, Fanhua Shang, Liang Wan, Wei Feng
Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models that are biased towards classes with sufficient samples and perform poorly on rare classes.
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.
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.
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.
no code implementations • ICCV 2023 • Fan Lyu, Qing Sun, Fanhua Shang, Liang Wan, Wei Feng
In Parallel Continual Learning (PCL), the parallel multiple tasks start and end training unpredictably, thus suffering from training conflict and catastrophic forgetting issues.
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.
1 code implementation • 25 Sep 2022 • Qing Sun, Fan Lyu, Fanhua Shang, Wei Feng, Liang Wan
Continual Learning (CL) sequentially learns new tasks like human beings, with the goal to achieve better Stability (S, remembering past tasks) and Plasticity (P, adapting to new tasks).
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.
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.
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.
no code implementations • 29 Sep 2021 • Qing Sun, Fan Lyu, Fanhua Shang, Wei Feng, Liang Wan
Traditionally, the primary goal of LL is to achieve the trade-off between the Stability (remembering past tasks) and Plasticity (adapting to new tasks).
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.
no code implementations • 26 Dec 2020 • Fan Lyu, Fuyuan Hu, Victor S. Sheng, Zhengtian Wu, Qiming Fu, Baochuan Fu
Since multi-label image classification is very complicated, people seek to use the attention mechanism to guide the classification process.
no code implementations • 14 Dec 2020 • Fan Lyu, Shuai Wang, Wei Feng, Zihan Ye, Fuyuan Hu, Song Wang
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 of previous knowledge when moving to new tasks.
1 code implementation • 19 May 2020 • Zihan Ye, Fuyuan Hu, Yin Liu, Zhenping Xia, Fan Lyu, Pengqing Liu
First, CNL computes correlations between features of a query layer and all response layers.
no code implementations • 24 Mar 2020 • Zhongguo Li, Fan Lyu, Wei Feng, Song Wang
Paired egocentric interaction recognition (PEIR) is the task to collaboratively recognize the interactions between two persons with the videos in their corresponding views.
no code implementations • 18 Mar 2020 • Shuai Wang, Fan Lyu, Wei Feng, Song Wang
In this paper, we argue that for REC the referring expression and the target region are semantically correlated and subject, location and relationship consistency exist between vision and language. On top of this, we propose a novel approach called MutAtt to construct mutual guidance between vision and language, which treat vision and language equally thus yield compact information matching.
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.
no code implementations • CVPR 2018 • Chaorui Deng, Qi Wu, Qingyao Wu, Fuyuan Hu, Fan Lyu, Mingkui Tan
There are three main challenges in VG: 1) what is the main focus in a query; 2) how to understand an image; 3) how to locate an object.