The paper focuses on interrogating the effect of the IceNet's input feature with a gradient-based analysis.

Introducing the SuperCM technique to significantly improve classification results across various types of image data.

Training and test data from different clients pose a challenge.

We propose DeepMVC – a unified framework which includes many recent methods as instances.

We approach the representation learning task by tackling the hubness problem.

ProtoVAE explainability paper by Srishti Gautam and co-authors is published to NeurIPS 2022.

We present a novel pyramid attention and gated fusion method (MultiModNet) for multi-modality land cover mapping in remote sensing.

How can we remove the redundant or less-informative edges in a graph without changing its main structural properties?

Exploiting limited data to perform objective measurements in ultrasound images of the heart.

We collaborate with the Institute of Marine Research (IMR) to develop models and applications to detect and classify fish from echosounders.

Visual intelligence is collaborating with Equinor to develop models that can exploit seismicdata and model the continuity of the subsurface.

Visual Intelligence collaborates with KSAT to improve existing, and develop new algorithms, for vessel detection and object recognition.

Deep learning and AI models must become interpretable, explainable and reliable before they can be utilized in complex domains.

Overcoming the challenges of limited training data in the medical domain and laying the fundamentals for explainability and reliability.

A collaboration with Terratec to develop deep learning methods to automatically detect changes when updating an existing map database.

Visual Intelligence collaborates with KSAT to develop new models for detecting and characterizing oil spills.

Better solutions are needed to estimate the populations of sea mammals, such as breeding seals, from aerial images of the sea ice.