Search Results for author:
Found 7 papers, 2 papers with code
Induced Feature Selection by Structured Pruning
The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years.
People Tracking and Re-Identifying in Distributed Contexts: Extension Study of PoseTReID
We use a well-known bounding box detector YOLO (v4) for the detection to compare to OpenPose which was used in our last paper, and we use SORT and DeepSORT to compare to centroid which was also used previously, and most importantly for the re-identification, we use a bunch of deep leaning methods such as MLFN, OSNet, and OSNet-AIN with our custom classification layer to compare to FaceNet which was also used earlier in our last paper.
Improve Convolutional Neural Network Pruning by Maximizing Filter Variety
This technique ensures that the criteria of selection focuses on redundant filters, while retaining the rare ones, thus maximizing the variety of remaining filters.
An Experimental Study of the Impact of Pre-training on the Pruning of a Convolutional Neural Network
Neural networks usually involve a large number of parameters, which correspond to the weights of the network.
DeepRare: Generic Unsupervised Visual Attention Models
In this paper, we propose a new visual attention model called DeepRare2021 (DR21) which uses the power of DNNs feature extraction and the genericity of feature-engineered algorithms.
One-Cycle Pruning: Pruning ConvNets Under a Tight Training Budget
Most of the time, sparsity is introduced using a three-stage pipeline: 1) train the model to convergence, 2) prune the model according to some criterion, 3) fine-tune the pruned model to recover performance.
A study of parameters affecting visual saliency assessment
In this paper, a new framework is proposed to assess models of visual saliency.
