no code implementations • 19 Jan 2022 • Arthi Padmanabhan, Neil Agarwal, Anand Iyer, Ganesh Ananthanarayanan, Yuanchao Shu, Nikolaos Karianakis, Guoqing Harry Xu, Ravi Netravali
Video analytics pipelines have steadily shifted to edge deployments to reduce bandwidth overheads and privacy violations, but in doing so, face an ever-growing resource tension.
no code implementations • 19 Dec 2020 • Romil Bhardwaj, Zhengxu Xia, Ganesh Ananthanarayanan, Junchen Jiang, Nikolaos Karianakis, Yuanchao Shu, Kevin Hsieh, Victor Bahl, Ion Stoica
Compressed models that are deployed on the edge servers for inference suffer from data drift, where the live video data diverges from the training data.
1 code implementation • ACCV 2020 • Jedrzej Kozerawski, Victor Fragoso, Nikolaos Karianakis, Gaurav Mittal, Matthew Turk, Mei Chen
Unfortunately, this imbalance enables a visual recognition system to perform well on head classes but poorly on tail classes.
Ranked #54 on Long-tail Learning on ImageNet-LT
no code implementations • CVPR 2020 • Gaurav Mittal, Chang Liu, Nikolaos Karianakis, Victor Fragoso, Mei Chen, Yun Fu
To reduce HPO time, we present HyperSTAR (System for Task Aware Hyperparameter Recommendation), a task-aware method to warm-start HPO for deep neural networks.
1 code implementation • 17 Nov 2019 • Fuxun Yu, Di Wang, Yinpeng Chen, Nikolaos Karianakis, Tong Shen, Pei Yu, Dimitrios Lymberopoulos, Sidi Lu, Weisong Shi, Xiang Chen
In this work, we show that such adversarial-based methods can only reduce the domain style gap, but cannot address the domain content distribution gap that is shown to be important for object detectors.
no code implementations • 27 Sep 2018 • Jiahuan Zhou, Nikolaos Karianakis, Ying Wu, Gang Hua
Current Convolutional Neural Network (CNN)-based object detection models adopt strictly feedforward inference to predict the final detection results.
no code implementations • ECCV 2018 • Nikolaos Karianakis, Zicheng Liu, Yinpeng Chen, Stefano Soatto
We address the problem of person re-identification from commodity depth sensors.
no code implementations • CVPR 2015 • Jingming Dong, Nikolaos Karianakis, Damek Davis, Joshua Hernandez, Jonathan Balzer, Stefano Soatto
We frame the problem of local representation of imaging data as the computation of minimal sufficient statistics that are invariant to nuisance variability induced by viewpoint and illumination.
no code implementations • CVPR 2016 • Nikolaos Karianakis, Jingming Dong, Stefano Soatto
We conduct an empirical study to test the ability of Convolutional Neural Networks (CNNs) to reduce the effects of nuisance transformations of the input data, such as location, scale and aspect ratio.
no code implementations • 21 Mar 2015 • Nikolaos Karianakis, Thomas J. Fuchs, Stefano Soatto
Modern detection algorithms like Regions with CNNs (Girshick et al., 2014) rely on Selective Search (Uijlings et al., 2013) to propose regions which with high probability represent objects, where in turn CNNs are deployed for classification.
no code implementations • 20 Dec 2014 • Stefano Soatto, Jingming Dong, Nikolaos Karianakis
We study the structure of representations, defined as approximations of minimal sufficient statistics that are maximal invariants to nuisance factors, for visual data subject to scaling and occlusion of line-of-sight.