Paced-Curriculum Distillation with Prediction and Label Uncertainty for Image Segmentation

1 code implementation • 2 Feb 2023 • Mobarakol Islam, Lalithkumar Seenivasan, S. P. Sharan, V. K. Viekash, Bhavesh Gupta, Ben Glocker, Hongliang Ren

Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress.

Image Segmentation Medical Image Segmentation +3

FAZSeg: A New User-Friendly Software for Quantification of the Foveal Avascular Zone

1 code implementation • 22 Nov 2021 • V. K. Viekash, Janarthanam Jothi Balaji, Vasudevan Lakshminarayanan

Various ocular diseases and high myopia influence the anatomical reference point Foveal Avascular Zone (FAZ) dimensions.

'CADSketchNet' -- An Annotated Sketch dataset for 3D CAD Model Retrieval with Deep Neural Networks

1 code implementation • 13 Jul 2021 • Bharadwaj Manda, Shubham Dhayarkar, Sai Mitheran, V. K. Viekash, Ramanathan Muthuganapathy

Using the sketch images from this dataset, the paper also aims at evaluating the performance of various retrieval system or a search engine for 3D CAD models that accepts a sketch image as the input query.

Retrieval