Published in arXiv, 2017
In this paper we introduce ShiftCNN, a generalized low-precision architecture for inference of multiplierless convolutional neural networks (CNNs).
Download here
Published in CEFRL @ ECCV, 2018
In this paper, we introduce a method to compress intermediate feature maps of deep neural networks (DNNs) to decrease memory storage and bandwidth requirements during inference.
Download here
Published in SysML @ NeurIPS, 2018
In this paper, we propose a practical approach to interpret decisions made by a DNN object detector that has fidelity comparable to state-of-the-art methods and sufficient computational efficiency to process large datasets.
Download here
Published in LLD @ ICLR, 2019
We introduce an attention mechanism to improve feature extraction for deep active learning (AL) in the semi-supervised setting.
Download here
Published in NeurIPS Demo, 2019
In this paper, we apply state-of-the-art visual reasoning model and demonstrate that it is feasible to ask a smart fridge about its contents and various properties of the food with close-to-natural conversation experience.
Download here
Published in CVPR, 2020
The main motivation of this paper is to consider a realistic setting for pool-based semi-supervised AL, where the unlabeled collection of train data is biased. We theoretically derive an optimal acquisition function for AL in this setting. It can be formulated as distribution shift minimization between unlabeled train data and weakly-labeled validation dataset.
Download here
Published in CVPR, 2021
While recent papers evolved in the direction of decreasing policy search complexity, we show that those methods are not robust when applied to biased and noisy data. To overcome these limitations, we reformulate AutoAugment as a generalized automated dataset optimization (AutoDO) task that minimizes the distribution shift between test data and distorted train dataset.
Download here
Published in WACV 2022, 2021
We propose a real-time (faster and smaller by a factor of 10x than prior state-of-the-art) model for unsupervised anomaly detection and analytically derive its relationship to prior methods. Our CFLOW-AD model is based on a conditional normalizing flow framework adopted for anomaly detection with localization.
Download here