Rumeng Yi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Rumeng Yi has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Yaping Huang
Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence, Beijing Jiaotong University, Beijing, China
3 shared publications - Daoying Geng
Department of Radiology, Huashan Hospital, Fudan University, Shanghai, P. R. China
1 shared publication - Hao Wu
Department of Dermatology, Huashan Hospital, Fudan University, Shanghai 200040, China
1 shared publication - Jie Liu
Beijing Jiaotong University, Beijing, People’s Republic of China
1 shared publication - Mengyang Pu
School of Control and Computer Engineering, North China Electric Power University, Beijing, China
1 shared publication - Peng Du
Department of Radiology, The Second Affiliated Hospital of Xuzhou Medical University
1 shared publication
Latest Publications
- 23 April 2024
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 175, 108503
SRTRP-Net: A multi-task learning network for segmentation and prediction of stereotactic radiosurgery treatment response in brain metastases
- 23 April 2024
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 175, 108503
SRTRP-Net: A multi-task learning network for segmentation and prediction of stereotactic radiosurgery treatment response in brain metastases
- 27 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 7700-7708
Mutual Filter Teaching for Open-Set Semi-Supervised Learning
Open-set semi-supervised learning (OSSL) provides a practical solution by filtering out-of-distribution (OOD) samples from unlabeled data to guarantee the reliance on large unlabeled data in semi-supervised setting. However, existing OSSL methods mainly focus on identifying in-distribution (ID) samples and discarding OOD samples, while ignoring to make full use of samples that could not be exactly identified as ID or OOD samples. Those samples are more likely to be hard samples, which should be carefully explored to boost the performance in OSSL task. Hence, in this paper, we propose a novel framework, named Mutual Filter Teaching (MFT), where two networks are trained simultaneously to divide the unlabeled data into three parts: ID samples, OOD samples and hard samples. The samples are regarded as ID or OOD samples only if two networks give consistent decisions according to Mahalanobis distance between the unlabeled samples and their closest class prototypes. For those samples with inconsistent decisions, we treat them as hard samples and design an efficient mutual teaching scheme where the samples detected by only one network as positive samples are fed to its peer network for training. Furthermore, we propose to employ the prediction variance of two networks to dynamically rectify the learning from hard samples. Experiments on multiple benchmark datasets demonstrate that our approach achieves the state-of-the-art performance.
- 27 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 7700-7708
Mutual Filter Teaching for Open-Set Semi-Supervised Learning
Open-set semi-supervised learning (OSSL) provides a practical solution by filtering out-of-distribution (OOD) samples from unlabeled data to guarantee the reliance on large unlabeled data in semi-supervised setting. However, existing OSSL methods mainly focus on identifying in-distribution (ID) samples and discarding OOD samples, while ignoring to make full use of samples that could not be exactly identified as ID or OOD samples. Those samples are more likely to be hard samples, which should be carefully explored to boost the performance in OSSL task. Hence, in this paper, we propose a novel framework, named Mutual Filter Teaching (MFT), where two networks are trained simultaneously to divide the unlabeled data into three parts: ID samples, OOD samples and hard samples. The samples are regarded as ID or OOD samples only if two networks give consistent decisions according to Mahalanobis distance between the unlabeled samples and their closest class prototypes. For those samples with inconsistent decisions, we treat them as hard samples and design an efficient mutual teaching scheme where the samples detected by only one network as positive samples are fed to its peer network for training. Furthermore, we propose to employ the prediction variance of two networks to dynamically rectify the learning from hard samples. Experiments on multiple benchmark datasets demonstrate that our approach achieves the state-of-the-art performance.
- 15 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 623-635
Learning From Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation
This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing approaches aim to generate accurate pixel-level labels from weak supervisions. However, we observe that those generated labels still inevitably contain noisy labels. Motivated by this observation, we present a novel perspective and formulate this task as a problem of learning with pixel-level label noise. Existing noisy label methods, nevertheless, mainly aim at image-level tasks, which can not capture the relationship between neighboring labels in one image. Therefore, we propose a graph-based label noise detection and correction framework to deal with pixel-level noisy labels. In particular, for the generated pixel-level noisy labels from weak supervisions by Class Activation Map (CAM), we train a clean segmentation model with strong supervisions to detect the clean labels from these noisy labels according to the cross-entropy loss. Then, we adopt a superpixel-based graph to represent the relations of spatial adjacency and semantic similarity between pixels in one image. Finally we correct the noisy labels using a Graph Attention Network (GAT) supervised by detected clean labels. We comprehensively conduct experiments on PASCAL VOC 2012, PASCAL-Context, MS-COCO and Cityscapes datasets. The experimental results show that our proposed semi-supervised method achieves the state-of-the-art performances and even outperforms the fully-supervised models on PASCAL VOC 2012 and MS-COCO datasets in some cases.
- 15 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 623-635
Learning From Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation
This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations (weak supervisions). Most existing approaches aim to generate accurate pixel-level labels from weak supervisions. However, we observe that those generated labels still inevitably contain noisy labels. Motivated by this observation, we present a novel perspective and formulate this task as a problem of learning with pixel-level label noise. Existing noisy label methods, nevertheless, mainly aim at image-level tasks, which can not capture the relationship between neighboring labels in one image. Therefore, we propose a graph-based label noise detection and correction framework to deal with pixel-level noisy labels. In particular, for the generated pixel-level noisy labels from weak supervisions by Class Activation Map (CAM), we train a clean segmentation model with strong supervisions to detect the clean labels from these noisy labels according to the cross-entropy loss. Then, we adopt a superpixel-based graph to represent the relations of spatial adjacency and semantic similarity between pixels in one image. Finally we correct the noisy labels using a Graph Attention Network (GAT) supervised by detected clean labels. We comprehensively conduct experiments on PASCAL VOC 2012, PASCAL-Context, MS-COCO and Cityscapes datasets. The experimental results show that our proposed semi-supervised method achieves the state-of-the-art performances and even outperforms the fully-supervised models on PASCAL VOC 2012 and MS-COCO datasets in some cases.
- 1 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (15209210) , 4328-4341
TC-Net: Detecting Noisy Labels Via Transform Consistency
It is crucial to distinguish mislabeled samples for dealing with noisy labels. Previous methods such as “Co-teaching” and “JoCoR” introduce two different networks to select clean samples out of the noisy ones and only use these clean samples to train the deep models. Different from these methods which require to train two networks simultaneously, we propose a simple and effective method to identify clean samples only using one single network. We discover that the clean samples prefer to reach consistent predictions for the original images and the transformed images while noisy samples usually suffer from inconsistent predictions. Motivated by this observation, we propose a noisy label detection approach, named Transform Consistency Network (TC-Net), which constrains the transform consistency ( i.e., category consistency and visual attention consistency) between the original images and the transformed images for network training. Then we can select small-loss samples to update the parameters of the network. Furthermore, in order to mitigate the negative influence of noisy labels, we design a classification loss by using the off-line hard labels and on-line soft labels to provide more reliable supervisions for training a robust model. We conduct comprehensive experiments on CIFAR-10, CIFAR-100 and Clothing1M datasets. Compared with the clean sample selection baselines, we achieve the state-of-the-art performance. Especially, in most cases, our proposed method outperforms the baselines by a large margin.
- 1 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 24 (15209210) , 4328-4341
TC-Net: Detecting Noisy Labels Via Transform Consistency
It is crucial to distinguish mislabeled samples for dealing with noisy labels. Previous methods such as “Co-teaching” and “JoCoR” introduce two different networks to select clean samples out of the noisy ones and only use these clean samples to train the deep models. Different from these methods which require to train two networks simultaneously, we propose a simple and effective method to identify clean samples only using one single network. We discover that the clean samples prefer to reach consistent predictions for the original images and the transformed images while noisy samples usually suffer from inconsistent predictions. Motivated by this observation, we propose a noisy label detection approach, named Transform Consistency Network (TC-Net), which constrains the transform consistency ( i.e., category consistency and visual attention consistency) between the original images and the transformed images for network training. Then we can select small-loss samples to update the parameters of the network. Furthermore, in order to mitigate the negative influence of noisy labels, we design a classification loss by using the off-line hard labels and on-line soft labels to provide more reliable supervisions for training a robust model. We conduct comprehensive experiments on CIFAR-10, CIFAR-100 and Clothing1M datasets. Compared with the clean sample selection baselines, we achieve the state-of-the-art performance. Especially, in most cases, our proposed method outperforms the baselines by a large margin.