36 citations · 46 across the 4 of their papers we have counts for
4 papers
Extending Decoupled Attention to Dense Prediction and Masked Training for Multi-Channel Images
Umar Marikkar, Sameed Husain, Muhammad Awais +1
Multi-Channel imaging (MCI) data differs fundamentally from natural images, as each channel records a semantically distinct signal rather than a colour band. To adapt vision encode…
Understanding the Distributions of Aggregation Layers in Deep Neural Networks
Eng-Jon Ong, Sameed Husain, Miroslaw Bober
The process of aggregation is ubiquitous in almost all deep nets models. It functions as an important mechanism for consolidating deep features into a more compact representation,…
Cultivating DNN Diversity for Large Scale Video Labelling
Mikel Bober-Irizar, Sameed Husain, Eng-Jon Ong +1
We investigate factors controlling DNN diversity in the context of the Google Cloud and YouTube-8M Video Understanding Challenge. While it is well-known that ensemble methods impro…
Siamese Network of Deep Fisher-Vector Descriptors for Image Retrieval
Eng-Jon Ong, Sameed Husain, Miroslaw Bober
This paper addresses the problem of large scale image retrieval, with the aim of accurately ranking the similarity of a large number of images to a given query image. To achieve th…