Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse
is one of the main challenges in the area of model compression, and several high …

This paper delves into the results of two resource-constrained deep learning challenges,
part of the workshop on Resource-Efficient Deep Learning for Computer Vision (RCV) at …

Driven by significant improvements in architectural design and training pipelines, computer
visionhas recently experienced dramatic progress in terms of accuracy on classic …

$ L_0 $ regularization of neural networks is a fundamental problem. In addition to
regularizing models for better generalizability, $ L_0 $ regularization also applies to …

In the domain of multimedia and multimodal processing, the efficient handling of diverse
data streams such as images, video, and sensor data is paramount. Model compression and …

Deep convolutional neural networks (DCNN for short) are vulnerable to examples with small
perturbations. Improving DCNN's robustness is of great significance to the safety-critical …

Neural Network pruning is an increasingly popular way for producing compact and efficient
models, suitable for resource-limited environments, while preserving high performance …

Neural network pruning is a key technique towards engineering large yet scalable,
interpretable, and generalizable models. Prior work on the subject has developed largely …

Deep learning has become an integral part of a large number of important applications, and
many of the recent breakthroughs have been enabled by the ability to train very large …

Table 1 summarizes the training hyperparameters used for our experiments on CIFAR-100
[3] and ImageNet [6] datasets. The chosen hyperparameters are selected based on standard …