Federated learning with label distribution skew via logits calibration

J Zhang, Z Li, B Li, J Xu, S Wu… - … on Machine Learning, 2022 - proceedings.mlr.press
Traditional federated optimization methods perform poorly with heterogeneous data (ie,
accuracy reduction), especially for highly skewed data. In this paper, we investigate the label …

Rethinking the learning paradigm for dynamic facial expression recognition

H Wang, B Li, S Wu, S Shen, F Liu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Dynamic Facial Expression Recognition (DFER) is a rapidly develo** field that
focuses on recognizing facial expressions in video format. Previous research has …

Global-and-local collaborative learning for co-salient object detection

R Cong, N Yang, C Li, H Fu, Y Zhao… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
The goal of co-salient object detection (CoSOD) is to discover salient objects that commonly
appear in a query group containing two or more relevant images. Therefore, how to …

HRTransNet: HRFormer-driven two-modality salient object detection

B Tang, Z Liu, Y Tan, Q He - … on Circuits and Systems for Video …, 2022 - ieeexplore.ieee.org
The High-Resolution Transformer (HRFormer) can maintain high-resolution representation
and share global receptive fields. It is friendly towards salient object detection (SOD) in …

Learning implicit class knowledge for RGB-D co-salient object detection with transformers

N Zhang, J Han, N Liu - IEEE Transactions on Image …, 2022 - ieeexplore.ieee.org
RGB-D co-salient object detection aims to segment co-occurring salient objects when given
a group of relevant images and depth maps. Previous methods often adopt separate …

Tcnet: Co-salient object detection via parallel interaction of transformers and cnns

Y Ge, Q Zhang, TZ **ang, C Zhang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The purpose of co-salient object detection (CoSOD) is to detect the salient objects that co-
occur in a group of relevant images. CoSOD has been significantly prospered by recent …

Memory-aided contrastive consensus learning for co-salient object detection

P Zheng, J Qin, S Wang, TZ **ang… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Co-salient object detection (CoSOD) aims at detecting common salient objects within a
group of relevant source images. Most of the latest works employ the attention mechanism …

Attack can benefit: An adversarial approach to recognizing facial expressions under noisy annotations

J Zheng, B Li, SC Zhang, S Wu, L Cao… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Abstract The real-world Facial Expression Recognition (FER) datasets usually exhibit
complex scenarios with coupled noise annotations and imbalanced classes distribution …

Toward stable co-saliency detection and object co-segmentation

B Li, L Tang, S Kuang, M Song… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
In this paper, we present a novel model for simultaneous stable co-saliency detection
(CoSOD) and object co-segmentation (CoSEG). To detect co-saliency (segmentation) …

Re-thinking the relations in co-saliency detection

L Tang, B Li, S Kuang, M Song… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Co-salient object detection (CoSOD) aims to detect common salient objects sharing the
same attributes in an image group. The key issue of CoSOD is how to model the inter …