Related papers: Neural Image Compression with Quantization Rectifi…
Quantization has emerged as a promising direction for model compression. Recently, data-free quantization has been widely studied as a promising method to avoid privacy concerns, which synthesizes images as an alternative to real training…
Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. Key performance factors are weather resistance and the possibility to directly measure velocity. With a rising number of radar…
Tensor decomposition of convolutional and fully-connected layers is an effective way to reduce parameters and FLOP in neural networks. Due to memory and power consumption limitations of mobile or embedded devices, the quantization step is…
We show that introducing short-range attractive couplings between the weights of a neural network during training provides a novel avenue for model quantization. These couplings rapidly induce the discretization of a model's weight…
The Residual Quantization (RQ) framework is revisited where the quantization distortion is being successively reduced in multi-layers. Inspired by the reverse-water-filling paradigm in rate-distortion theory, an efficient regularization on…
Many classical encoding algorithms of Vector Quantization (VQ) of image compression that can obtain global optimal solution have computational complexity O(N). A pure quantum VQ encoding algorithm with probability of success near 100% has…
The quantization of neural networks for the mitigation of the nonlinear and components' distortions in dual-polarization optical fiber transmission is studied. Two low-complexity neural network equalizers are applied in three 16-QAM 34.4…
Recovering a high dynamic range (HDR) image from a single low dynamic range (LDR) image, namely inverse tone mapping (ITM), is challenging due to the lack of information in over- and under-exposed regions. Current methods focus exclusively…
The high efficiency in computation and storage makes hashing (including binary hashing and quantization) a common strategy in large-scale retrieval systems. To alleviate the reliance on expensive annotations, unsupervised deep hashing…
Implicit neural representations (INR) have been recently proposed as deep learning (DL) based solutions for image compression. An image can be compressed by training an INR model with fewer weights than the number of image pixels to map the…
Deep learning for computer vision depends on lossy image compression: it reduces the storage required for training and test data and lowers transfer costs in deployment. Mainstream datasets and imaging pipelines all rely on standard JPEG…
Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight parameters and/or…
We present a lossy image compression method based on deep convolutional neural networks (CNNs), which outperforms the existing BPG, WebP, JPEG2000 and JPEG as measured via multi-scale structural similarity (MS-SSIM), at the same bit rate.…
Accelerating deep neural network (DNN) inference on resource-limited devices is one of the most important barriers to ensuring a wider and more inclusive adoption. To alleviate this, DNN binary quantization for faster convolution and memory…
The search for image compression optimization techniques is a topic of constant interest both in and out of academic circles. One method that shows promise toward future improvements in this field is image colorization since image…
In this paper, we propose an image re-sampling compression method by learning virtual codec network (VCN) to resolve the non-differentiable problem of quantization function for image compression. Here, the image re-sampling not only refers…
While neural networks have been remarkably successful in a wide array of applications, implementing them in resource-constrained hardware remains an area of intense research. By replacing the weights of a neural network with quantized…
Large-scale image datasets are fundamental to deep learning, but their high storage demands pose challenges for deployment in resource-constrained environments. While existing approaches reduce dataset size by discarding samples, they often…
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference, especially when deploying to edge or IoT devices with limited computation capacity and power consumption budget. The uniform bit…
Thanks to their state-of-the-art performance, deep neural networks are increasingly used for object recognition. To achieve these results, they use millions of parameters to be trained. However, when targeting embedded applications the size…