Ujjwal Verma

selected publications

1. BDL-NeurIPS 2021

   Evaluating Predictive Uncertainty and Robustness to Distributional Shift Using Real World Data

   Lakara, Kumud, Bhandari, Akshat, Seth, Pratinav, and Verma, Ujjwal

   2021

   Abs HTML PDF

   Most machine learning models operate under the assumption that the training, testing and deployment data is independent and identically distributed (i.i.d.). This assumption does not generally hold true in a natural setting. Usually, the deployment data is subject to various types of distributional shifts. The magnitude of a model’s performance is proportional to this shift in the distribution of the dataset. Thus it becomes necessary to evaluate a model’s uncertainty and robustness to distributional shifts to get a realistic estimate of its expected performance on real-world data. Present methods to evaluate uncertainty and model’s robustness are lacking and often fail to paint the full picture. Moreover, most analysis so far has primarily focused on classification tasks. In this paper, we propose more insightful metrics for general regression tasks using the Shifts Weather Prediction Dataset. We also present an evaluation of the baseline methods using these metrics

2. NAACL - SMM4H

   BERT based Transformers lead the way in Extraction of Health Information from Social Media

   Ramesh, Sidharth, Tiwari, Abhiraj, Choubey, Parthivi, Kashyap, Saisha, Khose, Sahil, Lakara, Kumud, Singh, Nishesh, and Verma, Ujjwal

   In Proceedings of the Sixth Social Media Mining for Health (#SMM4H) Workshop and Shared Task 2021

   HTML PDF
3. IEEE JSTARS

   UVid-Net: Enhanced Semantic Segmentation of UAV Aerial Videos by Embedding Temporal Information

   Girisha*, S, Verma*, Ujjwal, Pai, Manohara Pai, and Pai, Radhika

   IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2021

   Abs HTML PDF

   Semantic segmentation of aerial videos has been extensively used for decision making in monitoring environmental changes, urban planning, and disaster management. The reliability of these decision support systems is dependent on the accuracy of the video semantic segmentation algorithms. The existing CNN based video semantic segmentation methods have enhanced the image semantic segmentation methods by incorporating an additional module such as LSTM or optical flow for computing temporal dynamics of the video which is a computational overhead. The proposed research work modifies the CNN architecture by incorporating temporal information to improve the efficiency of video semantic segmentation. In this work, an enhanced encoder-decoder based CNN architecture (UVid-Net) is proposed for UAV video semantic segmentation. The encoder of the proposed architecture embeds temporal information for temporally consistent labelling. The decoder is enhanced by introducing the feature-refiner module, which aids in accurate localization of the class labels. The proposed UVid-Net architecture for UAV video semantic segmentation is quantitatively evaluated on extended ManipalUAVid dataset. The performance metric mIoU of 0.79 has been observed which is significantly greater than the other state-of-the-art algorithms. Further, the proposed work produced promising results even for the pre-trained model of UVid-Net on urban street scene with fine tuning the final layer on UAV aerial videos.

4. RSC Adv.

   Thread integrated smart-phone imaging facilitates early turning point colorimetric assay for microbes

   Prabhu, Anusha, Nandagopal, Giri, Yegneswaran, Prakash Peralam, Prabhu, Vijendra, Verma, Ujjwal, and Mani, Naresh Kumar

   RSC Advances 2020

   HTML PDF
5. EURASIP JIVP

   Segmentation and size estimation of tomatoes from sequences of paired images

   Verma, Ujjwal, Rossant, Florence, and Bloch, Isabelle

   EURASIP Journal on Image and Video Processing 2015

   HTML PDF