ParaDiS: Parallelly Distributable Slimmable Neural Networks

no code implementations • 6 Oct 2021 • Alexey Ozerov, Anne Lambert, Suresh Kirthi Kumaraswamy

While inspired by slimmable networks allowing instant adaptation to resources on just one device, ParaDiS networks consist of several multi-device distributable configurations or switches that strongly share the parameters between them.

Image Super-Resolution

Detecting Human-Object Interaction with Mixed Supervision

no code implementations • 10 Nov 2020 • Suresh Kirthi Kumaraswamy, Miaojing Shi, Ewa Kijak

Human object interaction (HOI) detection is an important task in image understanding and reasoning.

Human-Object Interaction Detection Object +1

Transfer Learning in CNNs Using Filter-Trees

no code implementations • 27 Nov 2017 • Suresh Kirthi Kumaraswamy, PS Sastry, KR Ramakrishnan

A filter-tree corresponding to a filter in k^{th} convolu- tional layer of a CNN is a subnetwork consisting of the filter along with all its connections to filters in all preceding layers.

Transfer Learning