5 papers
Learning To Focus: Anatomy-Guided Attention Regularization for Medical Image Classification
Tonmoy Hossain, Atiqur Rahman, Farhana Hossain Swarnali +1
Medical image classification models are ideally expected to identify diagnostically relevant regions while making predictions, yet standard classification losses rarely provide spa…
Learning to Unify Deformable Shape and Texture Representations for Cardiac Video Classification
Tonmoy Hossain, Miaomiao Zhang
Deformable shape representations have proven to be robust complements to texture features in cardiac image classification, offering geometric priors that are invariant to imaging a…
Learning Group Actions In Disentangled Latent Image Representations
Farhana Hossain Swarnali, Miaomiao Zhang, Tonmoy Hossain
Modeling group actions on latent representations enables controllable transformations of high-dimensional image data. Prior works applying group-theoretic priors or modeling transf…
CoRLD: Contrastive Representation Learning Of Deformable Shapes In Images
Tonmoy Hossain, Miaomiao Zhang
Deformable shape representations, parameterized by deformations relative to a given template, have proven effective for improved image analysis tasks. However, their broader applic…
MGAug: Multimodal Geometric Augmentation in Latent Spaces of Image Deformations
Tonmoy Hossain, Miaomiao Zhang
Geometric transformations have been widely used to augment the size of training images. Existing methods often assume a unimodal distribution of the underlying transformations betw…