no code implementations • 26 May 2023 • Alon Harell, Yalda Foroutan, Nilesh Ahuja, Parual Datta, Bhavya Kanzariya, V. Srinivasa Somayaulu, Omesh Tickoo, Anderson de Andrade, Ivan V. Bajic
To meet this growing demand, several methods have been developed for image and video coding for machines.
1 code implementation • CVPR 2023 • Nilesh Ahuja, Parual Datta, Bhavya Kanzariya, V. Srinivasa Somayazulu, Omesh Tickoo
Optimizing the pipeline for both compression and task-performance requires high-quality estimates of the information-theoretic rate of the intermediate features.
no code implementations • 23 Nov 2022 • Ibrahima Ndiour, Nilesh Ahuja, Utku Genc, Omesh Tickoo
This paper presents a fast and principled approach for solving the visual anomaly detection and segmentation problem.
no code implementations • 24 Aug 2022 • Parual Datta, Nilesh Ahuja, V. Srinivasa Somayazulu, Omesh Tickoo
Split computing has emerged as a recent paradigm for implementation of DNN-based AI workloads, wherein a DNN model is split into two parts, one of which is executed on a mobile/client device and the other on an edge-server (or cloud).
1 code implementation • 16 Feb 2022 • Samet Akcay, Dick Ameln, Ashwin Vaidya, Barath Lakshmanan, Nilesh Ahuja, Utku Genc
This paper introduces anomalib, a novel library for unsupervised anomaly detection and localization.
no code implementations • 13 Sep 2021 • Ranganath Krishnan, Nilesh Ahuja, Alok Sinha, Mahesh Subedar, Omesh Tickoo, Ravi Iyer
We introduce supervised contrastive active learning (SCAL) and propose efficient query strategies in active learning based on the feature similarity (featuresim) and principal component analysis based feature-reconstruction error (fre) to select informative data samples with diverse feature representations.
no code implementations • 13 Sep 2021 • Ranganath Krishnan, Alok Sinha, Nilesh Ahuja, Mahesh Subedar, Omesh Tickoo, Ravi Iyer
This paper presents simple and efficient methods to mitigate sampling bias in active learning while achieving state-of-the-art accuracy and model robustness.
no code implementations • ICLR Workshop EBM 2021 • Ergin Utku Genc, Nilesh Ahuja, Ibrahima J Ndiour, Omesh Tickoo
This brief sketches initial progress towards a unified energy-based solution for the semi-supervised visual anomaly detection and localization problem.
no code implementations • 8 Dec 2020 • Ibrahima Ndiour, Nilesh Ahuja, Omesh Tickoo
We also show that the feature reconstruction error, which is the $L_2$-norm of the difference between the original feature and the pre-image of its embedding, is highly effective for OOD detection and in some cases superior to the log-likelihood scores.
no code implementations • 18 Dec 2019 • Javier Felip, Nilesh Ahuja, Omesh Tickoo
After each new sample operation, a set of tree leaves are subdivided for improving the approximation of the proposal distribution to the target density.
no code implementations • 3 Dec 2019 • Mahesh Subedar, Nilesh Ahuja, Ranganath Krishnan, Ibrahima J. Ndiour, Omesh Tickoo
In the second approach, we use Bayesian deep neural networks trained with mean-field variational inference to estimate model uncertainty associated with the predictions.
no code implementations • 22 May 2019 • Javier Felip, Nilesh Ahuja, David Gómez-Gutiérrez, Omesh Tickoo, Vikash Mansinghka
The underlying generative models are built from realistic simulation software, wrapped in a Bayesian error model for the gap between simulation outputs and real data.