6 papers
TBPos: Dataset for Large-Scale Precision Visual Localization
Masud Fahim, Ilona Söchting, Luca Ferranti +2
Image based localization is a classical computer vision challenge, with several well-known datasets. Generally, datasets consist of a visual 3D database that captures the modeled s…
SADT: Combining Sharpness-Aware Minimization with Self-Distillation for Improved Model Generalization
Masud An-Nur Islam Fahim, Jani Boutellier
Methods for improving deep neural network training times and model generalizability consist of various data augmentation, regularization, and optimization approaches, which tend to…
Decay2Distill: Leveraging spatial perturbation and regularization for self-supervised image denoising
Manisha Das Chaity, Masud An Nur Islam Fahim
Unpaired image denoising has achieved promising development over the last few years. Regardless of the performance, methods tend to heavily rely on underlying noise properties or a…
Rethinking gradient weights' influence over saliency map estimation
Masud An Nur Islam Fahim, Nazmus Saqib, Shafkat Khan Siam +1
Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network's prediction. Gradient-based methods are generally faster than other br…
Denoising single images by feature ensemble revisited
Masud An Nur Islam Fahim, Nazmus Saqib, Shafkat Khan Siam +1
Image denoising is still a challenging issue in many computer vision sub-domains. Recent studies show that significant improvements are made possible in a supervised setting. Howev…
Semi-supervised atmospheric component learning in low-light image problem
Masud An Nur Islam Fahim, Nazmus Saqib, Jung Ho Yub
Ambient lighting conditions play a crucial role in determining the perceptual quality of images from photographic devices. In general, inadequate transmission light and undesired a…