Attend Who is Weak: Pruning-assisted Medical Image Localization under Sophisticated and Implicit Imbalances

12/06/2022
by   Ajay Jaiswal, et al.
0

Deep neural networks (DNNs) have rapidly become a de facto choice for medical image understanding tasks. However, DNNs are notoriously fragile to the class imbalance in image classification. We further point out that such imbalance fragility can be amplified when it comes to more sophisticated tasks such as pathology localization, as imbalances in such problems can have highly complex and often implicit forms of presence. For example, different pathology can have different sizes or colors (w.r.t.the background), different underlying demographic distributions, and in general different difficulty levels to recognize, even in a meticulously curated balanced distribution of training data. In this paper, we propose to use pruning to automatically and adaptively identify hard-to-learn (HTL) training samples, and improve pathology localization by attending them explicitly, during training in supervised, semi-supervised, and weakly-supervised settings. Our main inspiration is drawn from the recent finding that deep classification models have difficult-to-memorize samples and those may be effectively exposed through network pruning <cit.> - and we extend such observation beyond classification for the first time. We also present an interesting demographic analysis which illustrates HTLs ability to capture complex demographic imbalances. Our extensive experiments on the Skin Lesion Localization task in multiple training settings by paying additional attention to HTLs show significant improvement of localization performance by ∼2-3%.

READ FULL TEXT

page 2

page 3

page 6

page 7

research
07/10/2023

SPLAL: Similarity-based pseudo-labeling with alignment loss for semi-supervised medical image classification

Medical image classification is a challenging task due to the scarcity o...
research
08/20/2021

Semi-supervised learning for medical image classification using imbalanced training data

Medical image classification is often challenging for two reasons: a lac...
research
07/29/2023

Class-Specific Distribution Alignment for Semi-Supervised Medical Image Classification

Despite the success of deep neural networks in medical image classificat...
research
08/09/2023

Rapid Training Data Creation by Synthesizing Medical Images for Classification and Localization

While the use of artificial intelligence (AI) for medical image analysis...
research
01/23/2019

Robust Learning at Noisy Labeled Medical Images:Applied to Skin Lesion Classification

Deep neural networks (DNNs) have achieved great success in a wide variet...
research
02/27/2019

FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference

The main obstacle to weakly supervised semantic image segmentation is th...
research
08/17/2023

How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?

Pruning has emerged as a powerful technique for compressing deep neural ...

Please sign up or login with your details

Forgot password? Click here to reset