67 citations · 234 across the 29 of their papers we have counts for
29 papers
Understanding Imbalanced Forgetting in Rehearsal-Based Class-Incremental Learning
Alberto Tamajo, Srinandan Dasmahapatra, Rahman Attar
Neural networks suffer from catastrophic forgetting in class-incremental learning (CIL) settings. Rehearsal$\unicode{x2013}$replaying a subset of past samples$\unicode{x2013}$is a…
Mini-Batch Class Composition Bias in Link Prediction
Kieran Maguire, Srinandan Dasmahapatra
Prior work on node classification has shown that Graph Neural Networks (GNNs) can learn representations that transfer across graphs, when underlying graph properties are shared. Fo…
Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantization
Christopher Subia-Waud, Srinandan Dasmahapatra
Weight-sharing quantization has emerged as a technique to reduce energy expenditure during inference in large neural networks by constraining their weights to a limited set of valu…
MatSpectNet: Material Segmentation Network with Domain-Aware and Physically-Constrained Hyperspectral Reconstruction
Yuwen Heng, Yihong Wu, Jiawen Chen +2
Achieving accurate material segmentation for 3-channel RGB images is challenging due to the considerable variation in a material's appearance. Hyperspectral images, which are sets…
DBAT: Dynamic Backward Attention Transformer for Material Segmentation with Cross-Resolution Patches
Yuwen Heng, Srinandan Dasmahapatra, Hansung Kim
The objective of dense material segmentation is to identify the material categories for every image pixel. Recent studies adopt image patches to extract material features. Although…
Rotation-Scale Equivariant Steerable Filters
Yilong Yang, Srinandan Dasmahapatra, Sasan Mahmoodi
Incorporating either rotation equivariance or scale equivariance into CNNs has proved to be effective in improving models' generalization performance. However, jointly integrating…