Weakly Supervised Learning with Side Information for Noisy Labeled Images

Cheng, Lele; Zhou, Xiangzeng; Li-ming, Zhao; Li, Dangwei; Shang, Hong; Zheng, Yun; Pan, Pan; Xu, Yinghui

doi:10.1007/978-3-030-58577-8_19

Cited by 23 publications

(13 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More detailed information can be seen in Table 1. General Recognition For general recognition, we use 7 public datasets including Aliproduct (Cheng et al 2020), GLDv2 (Weyand et al 2020), VeRI-Wild (Lou et al 2019), LogoDet-3K (Wang et al 2020b), iCartoonFace (Zheng et al 2020), SOP (Song et al 2016), Inshop (Liu et al 2016). These data sets are also used for general training, model distillation and deephash.…”

Section: Methodsmentioning

confidence: 99%

PP-ShiTu: A Practical Lightweight Image Recognition System

Wei¹,

Guo²,

Cui³

et al. 2021

Preprint

View full text Add to dashboard Cite

In recent years, image recognition applications have developed rapidly. A large number of studies and techniques have emerged in different fields, such as face recognition, pedestrian and vehicle re-identification, landmark retrieval, and product recognition. In this paper, we propose a practical lightweight image recognition system, named PP-ShiTu, consisting of the following 3 modules,mainbody detection, feature extraction and vector search. We introduce popular strategies including metric learning, deep hash, knowledge distillation and model quantization to improve accuracy and inference speed. With strategies above, PP-ShiTu works well in different scenarios with a set of models trained on a mixed dataset. Experiments on different datasets and benchmarks show that the system is widely effective in different domains of image recognition. All the above mentioned models are open-sourced and the code is available in the GitHub repository PaddleClas 1 on PaddlePaddle 2 .

show abstract

Section: Methodsmentioning

confidence: 99%

PP-ShiTu: A Practical Lightweight Image Recognition System

Wei¹,

Guo²,

Cui³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Three major strategies dealing with label noise are widely explored: robust model architecture, robust loss, and sample selection. Noise adaptation layer is often used in robust model design to estimate the noise transition matrix [45]. In addition, designing robust losses is also a hot topic for learning with noisy labels.…”

Section: Weakly Supervised Learning-based Classificationmentioning

confidence: 99%

Weakly Supervised Classification of Hyperspectral Image Based on Complementary Learning

Huang

Chen

2021

Remote Sensing

View full text Add to dashboard Cite

In recent years, supervised learning-based methods have achieved excellent performance for hyperspectral image (HSI) classification. However, the collection of training samples with labels is not only costly but also time-consuming. This fact usually causes the existence of weak supervision, including incorrect supervision where mislabeled samples exist and incomplete supervision where unlabeled samples exist. Focusing on the inaccurate supervision and incomplete supervision, the weakly supervised classification of HSI is investigated in this paper. For inaccurate supervision, complementary learning (CL) is firstly introduced for HSI classification. Then, a new method, which is based on selective CL and convolutional neural network (SeCL-CNN), is proposed for classification with noisy labels. For incomplete supervision, a data augmentation-based method, which combines mixup and Pseudo-Label (Mix-PL) is proposed. And then, a classification method, which combines Mix-PL and CL (Mix-PL-CL), is designed aiming at better semi-supervised classification capacity of HSI. The proposed weakly supervised methods are evaluated on three widely-used hyperspectral datasets (i.e., Indian Pines, Houston, and Salinas datasets). The obtained results reveal that the proposed methods provide competitive results compared to the state-of-the-art methods. For inaccurate supervision, the proposed SeCL-CNN has outperformed the state-of-the-art method (i.e., SSDP-CNN) by 0.92%, 1.84%, and 1.75% in terms of OA on the three datasets, when the noise ratio is 30%. And for incomplete supervision, the proposed Mix-PL-CL has outperformed the state-of-the-art method (i.e., AROC-DP) by 1.03%, 0.70%, and 0.82% in terms of OA on the three datasets, with 25 training samples per class.

show abstract

“…To reduce the influence of noisy data, Cheng et al. ( 10 ) presented a weakly supervised learning method using a side information network, which largely alleviates the negative impact of noisy image labels. Qu et al.…”

Section: Introductionmentioning

confidence: 99%

Breast Cancer Molecular Subtype Prediction on Pathological Images with Discriminative Patch Selection and Multi-Instance Learning

Liu

Shang

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

Molecular subtypes of breast cancer are important references to personalized clinical treatment. For cost and labor savings, only one of the patient’s paraffin blocks is usually selected for subsequent immunohistochemistry (IHC) to obtain molecular subtypes. Inevitable block sampling error is risky due to the tumor heterogeneity and could result in a delay in treatment. Molecular subtype prediction from conventional H&E pathological whole slide images (WSI) using the AI method is useful and critical to assist pathologists to pre-screen proper paraffin block for IHC. It is a challenging task since only WSI-level labels of molecular subtypes from IHC can be obtained without detailed local region information. Gigapixel WSIs are divided into a huge amount of patches to be computationally feasible for deep learning, while with coarse slide-level labels, patch-based methods may suffer from abundant noise patches, such as folds, overstained regions, or non-tumor tissues. A weakly supervised learning framework based on discriminative patch selection and multi-instance learning was proposed for breast cancer molecular subtype prediction from H&E WSIs. Firstly, co-teaching strategy using two networks was adopted to learn molecular subtype representations and filter out some noise patches. Then, a balanced sampling strategy was used to handle the imbalance in subtypes in the dataset. In addition, a noise patch filtering algorithm that used local outlier factor based on cluster centers was proposed to further select discriminative patches. Finally, a loss function integrating local patch with global slide constraint information was used to fine-tune MIL framework on obtained discriminative patches and further improve the prediction performance of molecular subtyping. The experimental results confirmed the effectiveness of the proposed AI method and our models outperformed even senior pathologists, which has the potential to assist pathologists to pre-screen paraffin blocks for IHC in clinic.

show abstract

Weakly Supervised Learning with Side Information for Noisy Labeled Images

Cited by 23 publications

References 24 publications

PP-ShiTu: A Practical Lightweight Image Recognition System

PP-ShiTu: A Practical Lightweight Image Recognition System

Weakly Supervised Classification of Hyperspectral Image Based on Complementary Learning

Breast Cancer Molecular Subtype Prediction on Pathological Images with Discriminative Patch Selection and Multi-Instance Learning

Contact Info

Product

Resources

About