Bin Li

Bin Li

Auto-generated profile, based on publicly available information

Bin Li

Fudan University, Shanghai, China

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
24 March 2024 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
MYMingzhao Yang
Mingzhao Yang
SSShangchao Su
Shangchao Su
BLBin Li
Bin Li
XXXiangyang Xue
Xiangyang Xue
Recently, semi-supervised federated learning (semi-FL) has been proposed to handle the commonly seen real-world scenarios with labeled data on the server and unlabeled data on the clients. However, existing methods face several challenges such as communication costs, data heterogeneity, and training pressure on client devices. To address these challenges, we introduce the powerful diffusion models (DM) into semi-FL and propose FedDISC, a Federated Diffusion-Inspired Semi-supervised Co-training method. Specifically, we first extract prototypes of the labeled server data and use these prototypes to predict pseudo-labels of the client data. For each category, we compute the cluster centroids and domain-specific representations to signify the semantic and stylistic information of their distributions. After adding noise, these representations are sent back to the server, which uses the pre-trained DM to generate synthetic datasets complying with the client distributions and train a global model on it. With the assistance of vast knowledge within DM, the synthetic datasets have comparable quality and diversity to the client images, subsequently enabling the training of global models that achieve performance equivalent to or even surpassing the ceiling of supervised centralized training. FedDISC works within one communication round, does not require any local training, and involves very minimal information uploading, greatly enhancing its practicality. Extensive experiments on three large-scale datasets demonstrate that FedDISC effectively addresses the semi-FL problem on non-IID clients and outperforms the compared SOTA methods. Sufficient visualization experiments also illustrate that the synthetic dataset generated by FedDISC exhibits comparable diversity and quality to the original client dataset, with a neglectable possibility of leaking privacy-sensitive information of the clients.

14 June 2024 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
QWQizao Wang
Qizao Wang
XQXuelin Qian
Xuelin Qian
BLBin Li
Bin Li
XXXiangyang Xue
Xiangyang Xue
Yanwei FuYanwei Fu
Yanwei Fu
Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior discriminative features and limited training samples. Existing methods mainly leverage auxiliary information to facilitate identity-relevant feature learning, including soft-biometrics features of shapes or gaits, and additional labels of clothing. However, this information may be unavailable in real-world applications. In this paper, we propose a novel FIne-grained Representation and Recomposition (FIRe 2 ) framework to tackle both limitations without any auxiliary annotation or data. Specifically, we first design a Fine-grained Feature Mining (FFM) module to separately cluster images of each person. Images with similar so-called fine-grained attributes ( e.g ., clothes and viewpoints) are encouraged to cluster together. An attribute-aware classification loss is introduced to perform fine-grained learning based on cluster labels, which are not shared among different people, promoting the model to learn identity-relevant features. Furthermore, to take full advantage of fine-grained attributes, we present a Fine-grained Attribute Recomposition (FAR) module by recomposing image features with different attributes in the latent space. It significantly enhances robust feature learning. Extensive experiments demonstrate that FIRe 2 can achieve state-of-the-art performance on five widely-used cloth-changing person Re-ID benchmarks. The code is available at https://github.com/QizaoWang/FIRe-CCReID.

26 April 2023 in Neural Networks
Verified
Journal Article
Closed access
SSShangchao Su
Shangchao Su
BLBin Li
Bin Li
XXXiangyang Xue
Xiangyang Xue

14 June 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Open access
JYJinyang Yuan
Jinyang Yuan
TCTonglin Chen
Tonglin Chen
BLBin Li
Bin Li
XXXiangyang Xue
Xiangyang Xue
Visual scenes are composed of visual concepts and have the property of combinatorial explosion. An important reason for humans to efficiently learn from diverse visual scenes is the ability of compositional perception, and it is desirable for artificial intelligence to have similar abilities. Compositional scene representation learning is a task that enables such abilities. In recent years, various methods have been proposed to apply deep neural networks, which have been proven to be advantageous in representation learning, to learn compositional scene representations via reconstruction, advancing this research direction into the deep learning era. Learning via reconstruction is advantageous because it may utilize massive unlabeled data and avoid costly and laborious data annotation. In this survey, we first outline the current progress on reconstruction-based compositional scene representation learning with deep neural networks, including development history and categorizations of existing methods from the perspectives of the modeling of visual scenes and the inference of scene representations; then provide benchmarks, including an open source toolbox to reproduce the benchmark experiments, of representative methods that consider the most extensively studied problem setting and form the foundation for other methods; and finally discuss the limitations of existing methods and future directions of this research topic.

22 December 2023 in Machine Learning
Verified
Journal Article
Closed access
PDF file
HYHaiyang Yu
Haiyang Yu
JCJingye Chen
Jingye Chen
BLBin Li
Bin Li
XXXiangyang Xue
Xiangyang Xue

1 August 2022 in IEEE Transactions on Intelligent Vehicles
Verified
Journal Article
Closed access
GXGuozeng Xian
Guozeng Xian
CJChangyun Ji
Changyun Ji
LZLin Zhou
Lin Zhou
GCGuang Chen
Guang Chen
JZJunping Zhang
Junping Zhang
JPJian Pu
Jian Pu
The application of artificial intelligence in autonomous driving is becoming increasingly extensive. LiDAR-based 3D point cloud panoptic segmentation is one of the most promising and arduous tasks. Although recent methods have produced promising results, most of them ignore the prior distribution of objects in the 3D point clouds. In this paper, we first investigate the distribution of objects around the heading of vehicles and observe that several objects are severely biased. On the basis of this observation, we use the bird's eye view (BEV) representation to project the 3D point clouds into a 2D image and divide the BEV projection into eight areas. For each area, we apply input-dependent convolution kernels to extract the local feature. These local features are concatenated to the panoptic backbone for panoptic segmentation. We validate our method on the validation and test sets of the SemanticKITTI dataset. The proposed method outperforms all state-of-the-art methods based on 2D projection in terms of higher panoptic quality scores.