activity
20172021
most citedHow Much Position Information Do Convolutional Neural Networks Encode?

94 citations · 206 across the 8 of their papers we have counts for

collaborators

15 papers

cs.CV2021

Simpler Does It: Generating Semantic Labels with Objectness Guidance

Md Amirul Islam, Matthew Kowal, Sen Jia +2

Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lac…

cs.CV2021

SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness

Md Amirul Islam, Matthew Kowal, Konstantinos G. Derpanis +1

In this paper, we present a strategy for training convolutional neural networks to effectively resolve interference arising from competing hypotheses relating to inter-categorical…

cs.CV2021

Global Pooling, More than Meets the Eye: Position Information is Encoded Channel-Wise in CNNs

Md Amirul Islam, Matthew Kowal, Sen Jia +2

In this paper, we challenge the common assumption that collapsing the spatial dimensions of a 3D (spatial-channel) tensor in a convolutional neural network (CNN) into a vector via…

cs.CV202142 cited

Position, Padding and Predictions: A Deeper Look at Position Information in CNNs

Md Amirul Islam, Matthew Kowal, Sen Jia +2

In contrast to fully connected networks, Convolutional Neural Networks (CNNs) achieve efficiency by learning weights associated with local filters with a finite spatial extent. An…

cs.CV202115 cited

Shape or Texture: Understanding Discriminative Features in CNNs

Md Amirul Islam, Matthew Kowal, Patrick Esser +4

Contrasting the previous evidence that neurons in the later layers of a Convolutional Neural Network (CNN) respond to complex object shapes, recent studies have shown that CNNs act…

cs.CV2020

Bidirectional Attention Network for Monocular Depth Estimation

Shubhra Aich, Jean Marie Uwabeza Vianney, Md Amirul Islam +2

In this paper, we propose a Bidirectional Attention Network (BANet), an end-to-end framework for monocular depth estimation (MDE) that addresses the limitation of effectively integ…