no code implementations • 24 Mar 2024 • Dmitry A. Konovalov
The Mars Spectrometry 2: Gas Chromatography challenge was sponsored by NASA and run on the DrivenData competition platform in 2022.
1 code implementation • 28 Aug 2020 • Alzayat Saleh, Issam H. Laradji, Dmitry A. Konovalov, Michael Bradley, David Vazquez, Marcus Sheaves
The dataset consists of approximately 40 thousand images collected underwater from 20 \green{habitats in the} marine-environments of tropical Australia.
1 code implementation • 17 Sep 2019 • Dina B. Efremova, Mangalam Sankupellay, Dmitry A. Konovalov
In this research, we evaluated the effectiveness of birdcall classification using transfer learning from a larger base dataset (2814 samples in 46 classes) to a smaller target dataset (351 samples in 10 classes) using the ResNet-50 CNN.
no code implementations • 6 Sep 2019 • Dmitry A. Konovalov, Alzayat Saleh, Dina B. Efremova, Jose A. Domingos, Dean R. Jerry
The two CNNs were applied to the rest of the images and yielded automatically segmented masks.
no code implementations • 4 Aug 2019 • Dina B. Efremova, Dmitry A. Konovalov, Thanongchai Siriapisith, Worapan Kusakunniran, Peter Haddawy
We have chosen MICCAI 2017 LiTS dataset for training process and the public 3DIRCADb dataset for validation of our method.
no code implementations • 9 Jun 2019 • Dmitry A. Konovalov, Simindokht Jahangard, Lin Schwarzkopf
Cane toads are invasive, toxic to native predators, compete with native insectivores, and have a devastating impact on Australian ecosystems, prompting the Australian government to list toads as a key threatening process under the Environment Protection and Biodiversity Conservation Act 1999.
no code implementations • 26 May 2019 • Dmitry A. Konovalov, Alzayat Saleh, Michael Bradley, Mangalam Sankupellay, Simone Marini, Marcus Sheaves
Given a sufficiently large training dataset, it is relatively easy to train a modern convolution neural network (CNN) as a required image classifier.
1 code implementation • 9 Oct 2018 • Alex Olsen, Dmitry A. Konovalov, Bronson Philippa, Peter Ridd, Jake C. Wood, Jamie Johns, Wesley Banks, Benjamin Girgenti, Owen Kenny, James Whinney, Brendan Calvert, Mostafa Rahimi Azghadi, Ronald D. White
This work contributes the first large, public, multiclass image dataset of weed species from the Australian rangelands; allowing for the development of robust classification methods to make robotic weed control viable.