Srishti Gautam receiving award from Klas Henning Pettersen
Image:
Michael Kampffmeyer

Srishti Gautam receiving award from Klas Henning Pettersen

Srishti Gautam receives best poster award

Srishti Gautam, PhD student in Visual Intelligence, at UiT received the Best Poster award at the NORA annual conference 2022

Best poster award

We congratulate Srishti Gautam for her poster being voted to be the Best Poster at the NORA 2022 annual conference!

The poster was entitled "Demonstrating The Risk of Imbalanced Datasets in Chest X-ray Image-based Diagnostics by Prototypical Relevance Propagation" and is linked to the work done in her PhD project on advancing self-explainable deep-learning.

Srishti explains that the motivation for the work is to explore if a multi-source and label dataset favor learning from spurious artifacts, i.e, if text labels present in the  X-ray images can effect the disease classification. A second motivation is  how do self-explaining models deal with label-imbalanced datasets.

Deep neural networks can learn to exploit source-specific correlations when trained for classification by combining multi-source Chest X-Ray datasets. We hypothesize that this undesirable effect can be enforced by prevalence of a disease corresponding to a source/hospital. Therefore, we perform a thorough analysis of the effect of disease-imbalanced datasets from two hospitals for automated Pneumonia detection. The results show that a deep-learning model can behave as a hospital-detector instead of the intended Pneumonia-detector in the presence of high disease-imbalance. This further stresses the importance of using more faithful and transparent self-explaining models for automated medical diagnosis.

Visual intelligence Director Robert Jenssen Congratulates and expresses how proud he is to see the high-quality and hard work of our PhD student Srishti Gautam being acknowledged by the votes for the best poster.

The co-authors on the poster are: Marina M.-C. Hohne (Technical University of Berlin) Stine Hansen (UiT) Robert Jenssen (UiT), and Michael Kampffmeyer.

The work is done in the Visual Intelligence reseach centre and also supported by the German Ministry for Education and Research through the third-party funding project Explaining 4.0 (ref. 01IS20055).

‍

‍

‍

Latest news

Visual Intelligence Days 2026 was a success!

September 25, 2026

100 researchers, user partners and invited guests gathered in Oslo, Norway for the Visual Intelligence Days: the centre's annual conference for sharing knowledge and updates on the latest research and innovations.

Sciencenorway.no: Four reasons why you should not blindly trust artificial intelligence

September 19, 2026

Why should we think twice before using AI as a therapist, romantic partner, or to help out with homework? AI expert Elisabeth Wetzer explains (Popular science article on sciencenorway.no / forskning.no).

Associate Professor Kristoffer Wickstrøm interviewed by NRK Radio

September 18, 2026

Associate Professor Kristoffer Wickstrøm was interviewed by Norsk rikskringkasting (NRK) about the ongoing debate on whether to halt current and future AI development

Visual Intelligence well represented at Arendalsuka 2026

August 13, 2026

Visual Intelligence gathered experts from Norwegian politics, research council, industry, the public sector, and academia to discuss the value of Norwegian AI competence and Norwegian-developed models.

Two Visual Intelligence-authored papers accepted for MICCAI 2026

June 17, 2026

Visual Intelligence will be well represented at MICCAI 2026, one of the leading AI conferences on medical imaging and computer assisted intervention, with two accepted research papers.

Visual Intelligence represented at the Datacloud Global Congress' Talent in Tech programme

June 8, 2026

PhD Candidates Solveig Thrun and Christian Salomonsen attended the Datacloud Global Congress' Talent in Tech programme, which invited emerging talent to a unique programme designed to inspire, educate, and connect young professionals with senior leaders from global tech giants.

Kyst og Fjord: Råfisklaget tester AI-teknologi for å knipe syndere

June 2, 2026

En ny AI-løsning utviklet ved UiT kan gjøre det enklere å avdekke feilrapportering og ulovlig fiske. Nå skal Norges Råfisklag teste teknologien i praktisk bruk (News article on kystogfjord.no)

Geo365.no: Norges nye seismikkekspert

May 28, 2026

En ny, åpent tilgjengelig KI-modell kan endre hvordan geologer tolker seismikk. Den norske grunnmodellen lover raskere analyser, lavere terskel for innovasjon og nye måter å forstå undergrunnen på.