18 citations · 31 across the 7 of their papers we have counts for
8 papers
Fire Together Wire Together: A Dynamic Pruning Approach with Self-Supervised Mask Prediction
Sara Elkerdawy, Mostafa Elhoushi, Hong Zhang +1
Dynamic model pruning is a recent direction that allows for the inference of a different sub-network for each input sample during deployment. However, current dynamic methods rely…
Deep Snapshot HDR Reconstruction Based on the Polarization Camera
Juiwen Ting, Xuesong Wu, Kangkang Hu +1
The recent development of the on-chip micro-polarizer technology has made it possible to acquire four spatially aligned and temporally synchronized polarization images with the sam…
Polarimetric Monocular Dense Mapping Using Relative Deep Depth Prior
Moein Shakeri, Shing Yan Loo, Hong Zhang
This paper is concerned with polarimetric dense map reconstruction based on a polarization camera with the help of relative depth information as a prior. In general, polarization i…
To Filter Prune, or to Layer Prune, That Is The Question
Sara Elkerdawy, Mostafa Elhoushi, Abhineet Singh +2
Recent advances in pruning of neural networks have made it possible to remove a large number of filters or weights without any perceptible drop in accuracy. The number of parameter…
Semi-Supervised Monocular Depth Estimation with Left-Right Consistency Using Deep Neural Network
Ali Jahani Amiri, Shing Yan Loo, Hong Zhang
There has been tremendous research progress in estimating the depth of a scene from a monocular camera image. Existing methods for single-image depth prediction are exclusively bas…
Lightweight Monocular Depth Estimation Model by Joint End-to-End Filter pruning
Sara Elkerdawy, Hong Zhang, Nilanjan Ray
Convolutional neural networks (CNNs) have emerged as the state-of-the-art in multiple vision tasks including depth estimation. However, memory and computing power requirements rema…
Moving Object Detection under Discontinuous Change in Illumination Using Tensor Low-Rank and Invariant Sparse Decomposition
Moein Shakeri, Hong Zhang
Although low-rank and sparse decomposition based methods have been successfully applied to the problem of moving object detection using structured sparsity-inducing norms, they are…
Discriminative multi-view Privileged Information learning for image re-ranking
Jun Li, Chang Xu, Wankou Yang +3
Conventional multi-view re-ranking methods usually perform asymmetrical matching between the region of interest (ROI) in the query image and the whole target image for similarity c…