Related papers: PBGen: Partial Binarization of Deconvolution-Based…
Generative Adversarial Networks (GANs) have shown great promise in modeling high dimensional data. The learning objective of GANs usually minimizes some measure discrepancy, \textit{e.g.}, $f$-divergence~($f$-GANs) or Integral Probability…
Training of Generative Adversarial Networks (GANs) is notoriously fragile, requiring to maintain a careful balance between the generator and the discriminator in order to perform well. To mitigate this issue we introduce a new…
Generative Adversarial Networks (GANs) triggered an increased interest in problem of image generation due to their improved output image quality and versatility for expansion towards new methods. Numerous GAN-based works attempt to improve…
While hardware implementations of inference routines for Binarized Neural Networks (BNNs) are plentiful, current realizations of efficient BNN hardware training accelerators, suitable for Internet of Things (IoT) edge devices, leave much to…
Motivated by the necessity for parameter efficiency in distributed machine learning and AI-enabled edge devices, we provide a general and easy to implement method for significantly reducing the number of parameters of Convolutional Neural…
Deep learning is a rapidly developing approach in the field of infrared and visible image fusion. In this context, the use of dense blocks in deep networks significantly improves the utilization of shallow information, and the combination…
A good representation for arbitrarily complicated data should have the capability of semantic generation, clustering and reconstruction. Previous research has already achieved impressive performance on either one. This paper aims at…
Recent studies on Generative Adversarial Network (GAN) reveal that different layers of a generative CNN hold different semantics of the synthesized images. However, few GAN models have explicit dimensions to control the semantic attributes…
For the efficient execution of deep convolutional neural networks (CNN) on edge devices, various approaches have been presented which reduce the bit width of the network parameters down to 1 bit. Binarization of the first layer was always…
Deep Convolutional Neural Networks (CNNs) have been successfully used in many low-level vision problems like image denoising. Although the conditional image generation techniques have led to large improvements in this task, there has been…
A key enabler of deploying convolutional neural networks on resource-constrained embedded systems is the binary neural network (BNN). BNNs save on memory and simplify computation by binarizing both features and weights. Unfortunately,…
With the development of deep learning, the single super-resolution image reconstruction network models are becoming more and more complex. Small changes in hyperparameters of the models have a greater impact on model performance. In the…
Learned image compression has a problem of non-bit-exact reconstruction due to different calculations of floating point arithmetic on different devices. This paper shows a method to achieve a deterministic reconstructed image by quantizing…
Dense prediction is a critical task in computer vision. However, previous methods often require extensive computational resources, which hinders their real-world application. In this paper, we propose BiDense, a generalized binary neural…
Convolutional neural networks (CNNs) are able to attain better visual recognition performance than fully connected neural networks despite having much fewer parameters due to their parameter sharing principle. Modern architectures usually…
We introduce a novel weighted convolution operator that enhances traditional convolutional neural networks (CNNs) by integrating a spatial density function into the convolution operator. This extension enables the network to differentially…
Existing approaches towards single image dehazing including both model-based and learning-based heavily rely on the estimation of so-called transmission maps. Despite its conceptual simplicity, using transmission maps as an intermediate…
Deblurring is the task of restoring a blurred image to a sharp one, retrieving the information lost due to the blur. In blind deblurring we have no information regarding the blur kernel. As deblurring can be considered as an image to image…
Since its invention, Generative adversarial networks (GANs) have shown outstanding results in many applications. Generative Adversarial Networks are powerful yet, resource-hungry deep-learning models. Their main difference from ordinary…
Traditional generative adversarial networks (GAN) and many of its variants are trained by minimizing the KL or JS-divergence loss that measures how close the generated data distribution is from the true data distribution. A recent advance…