369 citations · 1.8k across the 93 of their papers we have counts for
10 papers · 1 filter
Self-supervised Learning with Fully Convolutional Networks
Zhengeng Yang, Hongshan Yu, Yong He +2
Although deep learning based methods have achieved great success in many computer vision tasks, their performance relies on a large number of densely annotated samples that are typ…
Defense-friendly Images in Adversarial Attacks: Dataset and Metrics for Perturbation Difficulty
Camilo Pestana, Wei Liu, David Glance +1
Dataset bias is a problem in adversarial machine learning, especially in the evaluation of defenses. An adversarial attack or defense algorithm may show better results on the repor…
Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking
ShiJie Sun, Naveed Akhtar, XiangYu Song +3
Deep learning-based Multiple Object Tracking (MOT) currently relies on off-the-shelf detectors for tracking-by-detection.This results in deep models that are detector biased and ev…
Image Colorization: A Survey and Dataset
Saeed Anwar, Muhammad Tahir, Chongyi Li +3
Image colorization estimates RGB colors for grayscale images or video frames to improve their aesthetic and perceptual quality. Over the last decade, deep learning techniques for i…
Fast ORB-SLAM without Keypoint Descriptors
Qiang Fu, Hongshan Yu, Xiaolong Wang +4
Indirect methods for visual SLAM are gaining popularity due to their robustness to environmental variations. ORB-SLAM2 \cite{orbslam2} is a benchmark method in this domain, however…
Cassandra: Detecting Trojaned Networks from Adversarial Perturbations
Xiaoyu Zhang, Ajmal Mian, Rohit Gupta +2
Deep neural networks are being widely deployed for many critical tasks due to their high classification accuracy. In many cases, pre-trained models are sourced from vendors who may…
Odyssey: Creation, Analysis and Detection of Trojan Models
Marzieh Edraki, Nazmul Karim, Nazanin Rahnavard +2
Along with the success of deep neural network (DNN) models, rise the threats to the integrity of these models. A recent threat is the Trojan attack where an attacker interferes wit…
Orthogonal Deep Models As Defense Against Black-Box Attacks
Mohammad A. A. K. Jalwana, Naveed Akhtar, Mohammed Bennamoun +1
Deep learning has demonstrated state-of-the-art performance for a variety of challenging computer vision tasks. On one hand, this has enabled deep visual models to pave the way for…
Minimum Potential Energy of Point Cloud for Robust Global Registration
Zijie Wu, Yaonan Wang, Qing Zhu +4
In this paper, we propose a novel minimum gravitational potential energy (MPE)-based algorithm for global point set registration. The feature descriptors extraction algorithms have…
Adversarial Perturbations Prevail in the Y-Channel of the YCbCr Color Space
Camilo Pestana, Naveed Akhtar, Wei Liu +2
Deep learning offers state of the art solutions for image recognition. However, deep models are vulnerable to adversarial perturbations in images that are subtle but significantly…