53 citations · 321 across the 50 of their papers we have counts for
6 papers · 1 filter
Single Image Deraining: From Model-Based to Data-Driven and Beyond
Wenhan Yang, Robby T. Tan, Shiqi Wang +2
The goal of single-image deraining is to restore the rain-free background scenes of an image degraded by rain streaks and rain accumulation. The early single-image deraining method…
Nighttime Stereo Depth Estimation using Joint Translation-Stereo Learning: Light Effects and Uninformative Regions
Aashish Sharma, Lionel Heng, Loong-Fah Cheong +1
Nighttime stereo depth estimation is still challenging, as assumptions associated with daytime lighting conditions do not hold any longer. Nighttime is not only about low-light and…
GraphX Chest X-Ray Classification Under Extreme Minimal Supervision
Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li +4
The task of classifying X-ray data is a problem of both theoretical and clinical interest. Whilst supervised deep learning methods rely upon huge amounts of labelled data, the crit…
Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy
Angelica I. Aviles-Rivero, Nicolas Papadakis, Ruoteng Li +4
Semi-supervised classification is a great focus of interest, as in real-world scenarios obtaining labels is expensive, time-consuming and might require expert knowledge. This has m…
Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning
Ruotent Li, Loong Fah Cheong, Robby T. Tan
Most deraining works focus on rain streaks removal but they cannot deal adequately with heavy rain images. In heavy rain, streaks are strongly visible, dense rain accumulation or r…
Certainty Driven Consistency Loss on Multi-Teacher Networks for Semi-Supervised Learning
Lu Liu, Robby T. Tan
One of the successful approaches in semi-supervised learning is based on the consistency regularization. Typically, a student model is trained to be consistent with teacher predict…