Search Results for author:
Found 8 papers, 5 papers with code
When Layers Play the Lottery, all Tickets Win at Initialization
In this work, we investigate LTH and pruning at initialization from the lens of layer pruning.
On the Effect of Pruning on Adversarial Robustness
However, studies have shown the potential of pruning as a form of regularization, which reduces overfitting and improves generalization.
Stage-Wise Neural Architecture Search
Motivated by this, we propose a NAS approach to efficiently design accurate and low-cost convolutional architectures and demonstrate that an efficient strategy for designing these architectures is to learn the depth stage-by-stage.
Covariance-free Partial Least Squares: An Incremental Dimensionality Reduction Method
Dimensionality reduction plays an important role in computer vision problems since it reduces computational cost and is often capable of yielding more discriminative data representation.
Pruning Deep Neural Networks using Partial Least Squares
Finally, we show that the proposed method achieves the highest FLOPs reduction and the smallest drop in accuracy when compared to state-of-the-art pruning approaches.
Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art
Inspired by this, we conduct an extensive set of experiments that analyze different sample generation processes and validation protocols to indicate the vulnerable points in human activity recognition based on wearable sensor data.
A Content-Based Late Fusion Approach Applied to Pedestrian Detection
We propose a novel method called Content-Based Spatial Consensus (CSBC), which, in addition to relying on spatial consensus, considers the content of the detection windows to learn a weighted-fusion of pedestrian detectors.
Latent hypernet: Exploring all Layers from Convolutional Neural Networks
To demonstrate the robustness and accuracy of the LHN, we evaluate it using four different networks architectures in five publicly available HAR datasets based on wearable sensors, which vary in the sampling rate and number of activities.
