Sichao Fu

Sichao Fu

Auto-generated profile, based on publicly available information

Sichao Fu

Huazhong University of Science and Technology

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2020 in Information Sciences
Verified
Journal Article
Closed access
SFSichao Fu
Sichao Fu
WLWeifeng Liu
Weifeng Liu
DTDapeng Tao
Dapeng Tao
YZYicong Zhou
Yicong Zhou
LNLiqiang Nie
Liqiang Nie

6 February 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
SFSichao Fu
Sichao Fu
QPQinmu Peng
Qinmu Peng
YHYang He
Yang He
XWXiaorui Wang
Xiaorui Wang
BZBin Zou
Bin Zou
XYXinge You
Xinge You
Unsupervised graph-structure learning (GSL) which aims to learn an effective graph structure applied to arbitrary downstream tasks by data itself without any labels’ guidance, has recently received increasing attention in various real applications. Although several existing unsupervised GSL has achieved superior performance in different graph analytical tasks, how to utilize the popular graph masked autoencoder to sufficiently acquire effective supervision information from the data itself for improving the effectiveness of learned graph structure has been not effectively explored so far. To tackle the above issue, we present a multilevel contrastive graph masked autoencoder (MCGMAE) for unsupervised GSL. Specifically, we first introduce a graph masked autoencoder with the dual feature masking strategy to reconstruct the same input graph-structured data under the original structure generated by the data itself and learned graph-structure scenarios, respectively. And then, the inter-and intra-class contrastive loss is introduced to maximize the mutual information in feature and graph-structure reconstruction levels simultaneously. More importantly, the above inter-and intra-class contrastive loss is also applied to the graph encoder module for further strengthening their agreement at the feature-encoder level. In comparison to the existing unsupervised GSL, our proposed MCGMAE can effectively improve the training robustness of the unsupervised GSL via different-level supervision information from the data itself. Extensive experiments on three graph analytical tasks and eight datasets validate the effectiveness of the proposed MCGMAE.

23 February 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
WWWuli Wang
Wuli Wang
LZLi Zhang
Li Zhang
SFSichao Fu
Sichao Fu
Peng RenPeng Ren
Peng Ren
GRGuangbo Ren
Guangbo Ren
BLBao-Di Liu
Bao-Di Liu
Few-shot class-incremental learning has recently received significant research focus in remote sensing scene classification (FSCIL-RSSC). The success of FSCIL-RSSC relies on the robustness of the feature backbone and classifiers. Existing works focus on improving classifier adaptation, but little attention is paid to the importance of backbone robustness on the recognition ability of new class samples’ embeddings. Due to the large distribution shift between old and new classes, FSCIL-RSSC utilizing high-layer (single-scale) features may not adapt flawlessly to new categories. To solve the issue, we put forward a Gradient Guided Multi-Scale Feature Collaboration Network (G-MFCN) for FSCIL-RSSC. Specifically, we introduce a parallel hierarchy strategy to simultaneously capture the multi-feature discriminative information of the same sample. Then, a gradient guide block is designed to automatically pick out the optimal values of different convolution blocks for multi-feature fusion. Finally, the classical feature pyramid network is introduced for multi-scale fusion to obtain more obvious discriminative features of RSSC. More importantly, our proposed G-MFCN is a simple and adaptable module, which can combine any existing FSCIL frameworks to further improve the optimized classifiers’ effectiveness for the FSCIL-RSSC scenario. Extensive experiments on four benchmarks demonstrate that the proposed G-MFCN achieves significant improvements in comparison to existing FSCIL-RSSC methods.

4 February 2022 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
ZZZhengqiang Zhang
Zhengqiang Zhang
QPQinmu Peng
Qinmu Peng
SFSichao Fu
Sichao Fu
WWWenjie Wang
Wenjie Wang
YCYiu-ming Cheung
Yiu-ming Cheung
XYXinge You
Xinge You
Recent weakly supervised semantic segmentation methods generate pseudolabels to recover the lost position information in weak labels for training the segmentation network. Unfortunately, those pseudolabels often contain mislabeled regions and inaccurate boundaries due to the incomplete recovery of position information. It turns out that the result of semantic segmentation becomes determinate to a certain degree. In this article, we decompose the position information into two components: high-level semantic information and low-level physical information, and develop a componentwise approach to recover each component independently. Specifically, we propose a simple yet effective pseudolabels updating mechanism to iteratively correct mislabeled regions inside objects to precisely refine high-level semantic information. To reconstruct low-level physical information, we utilize a customized superpixel-based random walk mechanism to trim the boundaries. Finally, we design a novel network architecture, namely, a dual-feedback network (DFN), to integrate the two mechanisms into a unified model. Experiments on benchmark datasets show that DFN outperforms the existing state-of-the-art methods in terms of intersection-over-union (mIoU).

30 August 2023 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
SFSichao Fu
Sichao Fu
QCQiong Cao
Qiong Cao
YLYunwen Lei
Yunwen Lei
YZYujie Zhong
Yujie Zhong
YZYibing Zhan
Yibing Zhan
XYXinge You
Xinge You
In recent years, few-shot learning has received increasing attention in the Internet of Things areas. Few-shot learning aims to distinguish unseen classes with a few labeled samples from each class. Most recently transductive few-shot studies highly rely on the static geometry distributions generated on the feature space during the label propagation process between unseen class instances. However, these recent methods fail to guarantee that the generated graph structure preserves the true distributions between data properly. In this article, we propose a novel dynamic graph structure preserving (DGSP) model for few-shot learning. Specifically, we formulate the objective function of DGSP by simultaneously considering the data correlations from the feature space and the label space to update the generated graph structure, which can reasonably revise the inappropriate or mistaken local geometry relationships. Then, we design an efficient alternating optimization algorithm to jointly learn the label prediction matrix and the optimal graph structure, the latter of which can be formulated as a linear programming problem. Moreover, our proposed DGSP can be easily combined with any backbone networks during the learning process. We conduct extensive experimental results across different benchmarks, backbones, and task settings, and our method achieves state-of-the-art performance compared with methods based on transductive few-shot learning.

14 August 2024 in Neural Networks
Verified
Journal Article
Closed access
SFSichao Fu
Sichao Fu
XMXueqi Ma
Xueqi Ma
YZYibing Zhan
Yibing Zhan
FYFanyu You
Fanyu You
QPQinmu Peng
Qinmu Peng
DMDanilo Mandic
Danilo Mandic