Related papers: MicroNet: Improving Image Recognition with Extreme…
This paper introduces Growing Networks with Autonomous Pruning (GNAP) for image classification. Unlike traditional convolutional neural networks, GNAP change their size, as well as the number of parameters they are using, during training,…
Neural network pruning has remarkable performance for reducing the complexity of deep network models. Recent network pruning methods usually focused on removing unimportant or redundant filters in the network. In this paper, by exploring…
Compressing images at extremely low bitrates (< 0.1 bpp) has always been a challenging task since the quality of reconstruction significantly reduces due to the strong imposed constraint on the number of bits allocated for the compressed…
Deeper and wider Convolutional Neural Networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such over-parameterized neural network has received increased attention. A typical pruning algorithm is a…
We propose ways to improve the performance of fully connected networks. We found that two approaches in particular have a strong effect on performance: linear bottleneck layers and unsupervised pre-training using autoencoders without hidden…
Dense optical flow estimation plays a key role in many robotic vision tasks. In the past few years, with the advent of deep learning, we have witnessed great progress in optical flow estimation. However, current networks often consist of a…
The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, able to perform more efficiently in resource-constrained…
The Deep Convolutional Neural Networks (CNNs) have obtained a great success for pattern recognition, such as recognizing the texts in images. But existing CNNs based frameworks still have several drawbacks: 1) the traditaional pooling…
Convolutional Neural Networks (CNNs) have achieved tremendous success in a number of learning tasks including image classification. Recent advanced models in CNNs, such as ResNets, mainly focus on the skip connection to avoid gradient…
The observation that activation sparsity emerges in MLP blocks of standardly trained Transformers offers an opportunity to drastically reduce computation costs without sacrificing performance. To theoretically explain this phenomenon,…
This paper presents a new version of Dropout called Split Dropout (sDropout) and rotational convolution techniques to improve CNNs' performance on image classification. The widely used standard Dropout has advantage of preventing deep…
Local feature detection is a key ingredient of many image processing and computer vision applications, such as visual odometry and localization. Most existing algorithms focus on feature detection from a sharp image. They would thus have…
Compact neural networks are inclined to exploit "sparsely-connected" convolutions such as depthwise convolution and group convolution for employment in mobile applications. Compared with standard "fully-connected" convolutions, these…
Compression of large and performant vision foundation models (VFMs) into arbitrary bit-wise operations (BitOPs) allows their deployment on various hardware. We propose to fine-tune a VFM to a mixed-precision quantized supernet. The…
Micro-expression recognition (MER), a critical subfield of affective computing, presents greater challenges than macro-expression recognition due to its brief duration and low intensity. While incorporating prior knowledge has been shown to…
Image convolutions have been a cornerstone of a great number of deep learning advances in computer vision. The research community is yet to settle on an equivalent operator for sparse, unstructured continuous data like point clouds and…
State-of-the-art deep learning models for computer vision tasks are based on the transformer architecture and often deployed in real-time applications. In this scenario, the resources available for every inference can vary, so it is useful…
Deep convolutional neural networks have achieved remarkable success in computer vision. However, deep neural networks require large computing resources to achieve high performance. Although depthwise separable convolution can be an…
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing. Recently,…
Considering the use of Fully Connected (FC) layer limits the performance of Convolutional Neural Networks (CNNs), this paper develops a method to improve the coupling between the convolution layer and the FC layer by reducing the noise in…