most citedSelf-Supervised Representation Learning for Visual Anomaly Detection

4 citations · 5 across the 3 of their papers we have counts for

collaborators

7 papers

cs.CV20201 cited

Increased-Range Unsupervised Monocular Depth Estimation

Saad Imran, Muhammad Umar Karim Khan, Sikander Bin Mukarram +1

Unsupervised deep learning methods have shown promising performance for single-image depth estimation. Since most of these methods use binocular stereo pairs for self-supervision,…

cs.CV20204 cited

Self-Supervised Representation Learning for Visual Anomaly Detection

Rabia Ali, Muhammad Umar Karim Khan, Chong Min Kyung

Self-supervised learning allows for better utilization of unlabelled data. The feature representation obtained by self-supervision can be used in downstream tasks such as classific…

cs.CV2020

Fine-Tuning DARTS for Image Classification

Muhammad Suhaib Tanveer, Muhammad Umar Karim Khan, Chong-Min Kyung

Neural Architecture Search (NAS) has gained attraction due to superior classification performance. Differential Architecture Search (DARTS) is a computationally light method. To li…

cs.CV2020

Global Feature Aggregation for Accident Anticipation

Mishal Fatima, Muhammad Umar Karim Khan, Chong Min Kyung

Anticipation of accidents ahead of time in autonomous and non-autonomous vehicles aids in accident avoidance. In order to recognize abnormal events such as traffic accidents in a v…

cs.CV2020

Plug-and-Play Anomaly Detection with Expectation Maximization Filtering

Muhammad Umar Karim Khan, Mishal Fatima, Chong-Min Kyung

Anomaly detection in crowds enables early rescue response. A plug-and-play smart camera for crowd surveillance has numerous constraints different from typical anomaly detection: th…

cs.CV2018

Efficient Neural Network Compression

Hyeji Kim, Muhammad Umar Karim Khan, Chong-Min Kyung

Network compression reduces the computational complexity and memory consumption of deep neural networks by reducing the number of parameters. In SVD-based network compression, the…