scholarly journals Adversarial Label Learning

2019 ◽  
Vol 33 ◽  
pp. 3183-3190
Author(s):  
Chidubem Arachie ◽  
Bert Huang
Keyword(s):  
Supervised Learning ◽  
Error Rate ◽  
Upper Bound ◽  
Training Data ◽  
Weakly Supervised Learning ◽  
Weak Supervision ◽  
Primal Dual ◽  
Weakly Supervised

We consider the task of training classifiers without labels. We propose a weakly supervised method—adversarial label learning—that trains classifiers to perform well against an adversary that chooses labels for training data. The weak supervision constrains what labels the adversary can choose. The method therefore minimizes an upper bound of the classifier’s error rate using projected primal-dual subgradient descent. Minimizing this bound protects against bias and dependencies in the weak supervision. Experiments on real datasets show that our method can train without labels and outperforms other approaches for weakly supervised learning.

scholarly journals AAWS-Net: Anatomy-aware weakly-supervised learning network for breast mass segmentation

PLoS ONE ◽  
2021 ◽  
Vol 16 (8) ◽  
pp. e0256830
Author(s):  
Yeheng Sun ◽  
Yule Ji
Keyword(s):  
Supervised Learning ◽  
Learning Strategy ◽  
Medical Image Analysis ◽  
Training Data ◽  
Breast Mass ◽  
Weakly Supervised Learning ◽  
Learning Network ◽  
Teacher Student ◽  
Mass Segmentation ◽  
Weakly Supervised

Accurate segmentation of breast masses is an essential step in computer aided diagnosis of breast cancer. The scarcity of annotated training data greatly hinders the model’s generalization ability, especially for the deep learning based methods. However, high-quality image-level annotations are time-consuming and cumbersome in medical image analysis scenarios. In addition, a large amount of weak annotations is under-utilized which comprise common anatomy features. To this end, inspired by teacher-student networks, we propose an Anatomy-Aware Weakly-Supervised learning Network (AAWS-Net) for extracting useful information from mammograms with weak annotations for efficient and accurate breast mass segmentation. Specifically, we adopt a weakly-supervised learning strategy in the Teacher to extract anatomy structure from mammograms with weak annotations by reconstructing the original image. Besides, knowledge distillation is used to suggest morphological differences between benign and malignant masses. Moreover, the prior knowledge learned from the Teacher is introduced to the Student in an end-to-end way, which improves the ability of the student network to locate and segment masses. Experiments on CBIS-DDSM have shown that our method yields promising performance compared with state-of-the-art alternative models for breast mass segmentation in terms of segmentation accuracy and IoU.

scholarly journals Weakly Supervised Learning for Evaluating Road Surface Condition from Wheelchair Driving Data

Information ◽  
2019 ◽  
Vol 11 (1) ◽  
pp. 2
Author(s):  
Takumi Watanabe ◽  
Hiroki Takahashi ◽  
Yusuke Iwasawa ◽  
Yutaka Matsuo ◽  
Ikuko Eguchi Yairi
Keyword(s):  
Supervised Learning ◽  
Surface Condition ◽  
Road Surface ◽  
Supervised Machine Learning ◽  
Accelerometer Data ◽  
Weakly Supervised Learning ◽  
Weak Supervision ◽  
Surface Conditions ◽  
Feature Representations ◽  
Weakly Supervised

Providing accessibility information about sidewalks for people with difficulties with moving is an important social issue. We previously proposed a fully supervised machine learning approach for providing accessibility information by estimating road surface conditions using wheelchair accelerometer data with manually annotated road surface condition labels. However, manually annotating road surface condition labels is expensive and impractical for extensive data. This paper proposes and evaluates a novel method for estimating road surface conditions without human annotation by applying weakly supervised learning. The proposed method only relies on positional information while driving for weak supervision to learn road surface conditions. Our results demonstrate that the proposed method learns detailed and subtle features of road surface conditions, such as the difference in ascending and descending of a slope, the angle of slopes, the exact locations of curbs, and the slight differences of similar pavements. The results demonstrate that the proposed method learns feature representations that are discriminative for a road surface classification task. When the amount of labeled data is 10% or less in a semi-supervised setting, the proposed method outperforms a fully supervised method that uses manually annotated labels to learn feature representations of road surface conditions.

scholarly journals Method for Automatic Term Extraction from Scientific Articles Based on Weak Supervision

2021 ◽  
Vol 19 (2) ◽  
pp. 5-16
Author(s):  
E. P. Bruches ◽  
T. V. Batura
Keyword(s):  
Supervised Learning ◽  
Additional Data ◽  
Weakly Supervised Learning ◽  
Weak Supervision ◽  
Term Extraction ◽  
Text Collections ◽  
Automatic Term Extraction ◽  
Scientific Terms ◽  
Weakly Supervised

We propose a method for scientific terms extraction from the texts in Russian based on weakly supervised learning. This approach doesn't require a large amount of hand-labeled data. To implement this method we collected a list of terms in a semi-automatic way and then annotated texts of scientific articles with these terms. These texts we used to train a model. Then we used predictions of this model on another part of the text collection to extend the train set. The second model was trained on both text collections: annotated with a dictionary and by a second model. Obtained results showed that giving additional data, annotated even in an automatic way, improves the quality of scientific terms extraction.

scholarly journals IWE-Net: Instance Weight Network for Locating Negative Comments and its application to improve Traffic User Experience

2020 ◽  
Vol 34 (04) ◽  
pp. 4052-4059
Author(s):  
Lan-Zhe Guo ◽  
Feng Kuang ◽  
Zhang-Xun Liu ◽  
Yu-Feng Li ◽  
Nan Ma ◽  
...  
Keyword(s):  
Supervised Learning ◽  
User Experience ◽  
Large Scale ◽  
Gradient Methods ◽  
Sampling Bias ◽  
Weakly Supervised Learning ◽  
Label Noise ◽  
Weak Supervision ◽  
Ride Sharing ◽  
Weakly Supervised

Weakly supervised learning aims at coping with scarce labeled data. Previous weakly supervised studies typically assume that there is only one kind of weak supervision in data. In many applications, however, raw data usually contains more than one kind of weak supervision at the same time. For example, in user experience enhancement from Didi, one of the largest online ride-sharing platforms, the ride comment data contains severe label noise (due to the subjective factors of passengers) and severe label distribution bias (due to the sampling bias). We call such a problem as ‘compound weakly supervised learning’. In this paper, we propose the CWSL method to address this problem based on Didi ride-sharing comment data. Specifically, an instance reweighting strategy is employed to cope with severe label noise in comment data, where the weights for harmful noisy instances are small. Robust criteria like AUC rather than accuracy and the validation performance are optimized for the correction of biased data label. Alternating optimization and stochastic gradient methods accelerate the optimization on large-scale data. Experiments on Didi ride-sharing comment data clearly validate the effectiveness. We hope this work may shed some light on applying weakly supervised learning to complex real situations.

scholarly journals Weakly Supervised Learning for Categorization of Medical Inquiries for Customer Service Effectiveness

2021 ◽  
Vol 6 ◽  
Author(s):  
Shikha Singhal ◽  
Bharat Hegde ◽  
Prathamesh Karmalkar ◽  
Justna Muhith ◽  
Harsha Gurulingappa
Keyword(s):  
Machine Learning ◽  
Natural Language Processing ◽  
Natural Language ◽  
Supervised Learning ◽  
Language Processing ◽  
Medical Information ◽  
Service Providers ◽  
Training Data ◽  
Weakly Supervised Learning ◽  
Weakly Supervised

With the growing unstructured data in healthcare and pharmaceutical, there has been a drastic adoption of natural language processing for generating actionable insights from text data sources. One of the key areas of our exploration is the Medical Information function within our organization. We receive a significant amount of medical information inquires in the form of unstructured text. An enterprise-level solution must deal with medical information interactions via multiple communication channels which are always nuanced with a variety of keywords and emotions that are unique to the pharmaceutical industry. There is a strong need for an effective solution to leverage the contextual knowledge of the medical information business along with digital tenants of natural language processing (NLP) and machine learning to build an automated and scalable process that generates real-time insights on conversation categories. The traditional supervised learning methods rely on a huge set of manually labeled training data and this dataset is difficult to attain due to high labeling costs. Thus, the solution is incomplete without its ability to self-learn and improve. This necessitates techniques to automatically build relevant training data using a weakly supervised approach from textual inquiries across consumers, healthcare professionals, sales, and service providers. The solution has two fundamental layers of NLP and machine learning. The first layer leverages heuristics and knowledgebase to identify the potential categories and build an annotated training data. The second layer, based on machine learning and deep learning, utilizes the training data generated using the heuristic approach for identifying categories and sub-categories associated with verbatim. Here, we present a novel approach harnessing the power of weakly supervised learning combined with multi-class classification for improved categorization of medical information inquiries.

Shape robust Siamese network tracking based on weakly supervised learning

2020 ◽  
pp. 2050057
Author(s):  
Ding Ma ◽  
Yong Zhou ◽  
Rui Yao ◽  
Jiaqi Zhao ◽  
Bing Liu ◽  
...  
Keyword(s):  
Target Tracking ◽  
Supervised Learning ◽  
Main Idea ◽  
Processing Method ◽  
Training Data ◽  
Tracking Accuracy ◽  
Weakly Supervised Learning ◽  
Siamese Network ◽  
Monitoring Framework ◽  
Weakly Supervised

This paper combines the boundary box regression with the training data occlusion processing method, the occlusion problem is more accurate and the tracking accuracy is improved. The occlusion problem is now the major challenge in target tracking. This paper puts forward a weakly monitoring framework to address this problem. The main idea is to randomly hide the most discriminating patches in the input images, forcing the network to focus on other relevant parts. Our method only needs to modify the inputs, no need to hide any patches during the test.

scholarly journals Safe Weakly Supervised Learning

2021 ◽  
Author(s):  
Yu-Feng Li
Keyword(s):  
Supervised Learning ◽  
Performance Improvement ◽  
Worst Case Analysis ◽  
Distribution Data ◽  
Improve Performance ◽  
Open Problems ◽  
Worst Case ◽  
Weakly Supervised Learning ◽  
Weak Supervision ◽  
Weakly Supervised

Weakly supervised learning (WSL) refers to learning from a large amount of weak supervision data. This includes i) incomplete supervision (e.g., semi-supervised learning); ii) inexact supervision (e.g., multi-instance learning) and iii) inaccurate supervision (e.g., label noise learning). Unlike supervised learning which typically achieves performance improvement with more labeled data, WSL may sometimes even degenerate performance with more weak supervision data. It is thus desired to study safe WSL, which could robustly improve performance with weak supervision data. In this article, we share our understanding of the problem from in-distribution data to out-of-distribution data, and discuss possible ways to alleviate it, from the aspects of worst-case analysis, ensemble-learning, and bi-level optimization. We also share some open problems, to inspire future researches.

Sign in / Sign up

Export Citation Format

Share Document