arXiv subjects

Zengqiang Yan

Publications and source records attributed to Zengqiang Yan.

21 records · Page 2Linked to original sources

arXiv2022

FedMix: Mixed Supervised Federated Learning for Medical Image Segmentation

The purpose of federated learning is to enable multiple clients to jointly train a machine learning model without sharing data. However, the existing methods for training an image segmentation model have been based on an unrealistic assumption that the training set for each local client is annotated in a similar fashion and thus follows the same image supervision level. To relax this assumption, in this work, we propose a label-agnostic unified federated learning framework, named FedMix, for medical image segmentation based on mixed image labels. In FedMix, each client updates the federated model by integrating and effectively making use of all available labeled data ranging from strong pixel-level labels, weak bounding box labels, to weakest image-level class labels. Based on these local models, we further propose an adaptive weight assignment procedure across local clients, where each client learns an aggregation weight during the global model update. Compared to the existing methods, FedMix not only breaks through the constraint of a single level of image supervision, but also can dynamically adjust the aggregation weight of each local client, achieving rich yet discriminative feature representations. To evaluate its effectiveness, experiments have been carried out on two challenging medical image segmentation tasks, i.e., breast tumor segmentation and skin lesion segmentation. The results validate that our proposed FedMix outperforms the state-of-the-art method by a large margin.

cs.CV↗

arXiv2021

Exploring intermediate representation for monocular vehicle pose estimation

We present a new learning-based framework to recover vehicle pose in SO(3) from a single RGB image. In contrast to previous works that map from local appearance to observation angles, we explore a progressive approach by extracting meaningful Intermediate Geometrical Representations (IGRs) to estimate egocentric vehicle orientation. This approach features a deep model that transforms perceived intensities to IGRs, which are mapped to a 3D representation encoding object orientation in the camera coordinate system. Core problems are what IGRs to use and how to learn them more effectively. We answer the former question by designing IGRs based on an interpolated cuboid that derives from primitive 3D annotation readily. The latter question motivates us to incorporate geometry knowledge with a new loss function based on a projective invariant. This loss function allows unlabeled data to be used in the training stage to improve representation learning. Without additional labels, our system outperforms previous monocular RGB-based methods for joint vehicle detection and pose estimation on the KITTI benchmark, achieving performance even comparable to stereo methods. Code and pre-trained models are available at this https URL.

cs.CV↗

arXiv2016

Describing upper body motions based on the Labanotation for learning-from-observation robots

We have been developing a paradigm, which we refer to as Learning-from-observation, for a robot to automatically acquire what-to-do through observation of human performance. Since a simple mimicking method to repeat exact joint angles does not work due to the kinematic and dynamic difference between a human and a robot, the method introduces an intermediate symbolic representation, task models, to conceptually represent what-to-do through observation. Then, these task models are mapped appropriate robot motions depending on each robot hardware. This paper presents task models, designed based on the Labanotation, for upper body movements of humanoid robots. Given a human motion sequence, we first analyze the motions of the upper body, and extract certain fixed poses at certain key frames. These key poses are translated into states represented by Labanotation symbols. Then, task models, identified from the state transitions, are mapped to robot movements on a particular robot hardware. Since the task models based on Labanotation are independent from different robot hardware, we can share the same observation module; we only need task mapping modules depending on different robot hardware. The system was implemented and demonstrated that three different robots can automatically mimic human upper body motions with satisfactory level of resemblance.

cs.RO↗