Related papers: Weighted Encoding Optimization for Dynamic Single-…
Deep Neural Networks (DNNs) have gained immense success in cognitive applications and greatly pushed today's artificial intelligence forward. The biggest challenge in executing DNNs is their extremely data-extensive computations. The…
We present an approach to accelerating a wide variety of image processing operators. Our approach uses a fully-convolutional network that is trained on input-output pairs that demonstrate the operator's action. After training, the original…
In this paper, we propose an ultrafast automated model compression framework called SeerNet for flexible network deployment. Conventional non-differen-tiable methods discretely search the desirable compression policy based on the accuracy…
In this paper a novel approach for de noising images corrupted by random valued impulses has been proposed. Noise suppression is done in two steps. The detection of noisy pixels is done using all neighbor directional weighted pixels (ANDWP)…
Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing…
Compressed Sensing refers to extracting a low-dimensional structured signal of interest from its incomplete random linear observations. A line of recent work has studied that, with the extra prior information about the signal, one can…
An increasing share of captured images and videos are transmitted for storage and remote analysis by computer vision algorithms, rather than to be viewed by humans. Contrary to traditional standard codecs with engineered tools, neural…
We introduce deep tensor networks, which are exponentially wide neural networks based on the tensor network representation of the weight matrices. We evaluate the proposed method on the image classification (MNIST, FashionMNIST) and…
We solve the analysis sparse coding problem considering a combination of convex and non-convex sparsity promoting penalties. The multi-penalty formulation results in an iterative algorithm involving proximal-averaging. We then unfold the…
Most of the existing denoising algorithms are developed for grayscale images, while it is not a trivial work to extend them for color image denoising because the noise statistics in R, G, B channels can be very different for real noisy…
Network quantization has rapidly become one of the most widely used methods to compress and accelerate deep neural networks. Recent efforts propose to quantize weights and activations from different layers with different precision to…
In this paper we describe weighting techniques used for the optimal coaddition of CCD frames with differing characteristics. Optimal means maximum signal-to-noise (s/n) for stellar objects. We derive formulae for four applications: 1)…
Minimal mutual coherence of discrete noiselets and Haar wavelets makes this pair of bases an essential choice for the measurement and compression matrices in compressed-sensing-based single-pixel detectors. In this paper we propose an…
Weight pruning is a powerful technique to realize model compression. We propose PCNN, a fine-grained regular 1D pruning method. A novel index format called Sparsity Pattern Mask (SPM) is presented to encode the sparsity in PCNN. Leveraging…
Existing deep calibrated photometric stereo networks basically aggregate observations under different lights based on the pre-defined operations such as linear projection and max pooling. While they are effective with the dense capture,…
Coded-illumination can enable quantitative phase microscopy of transparent samples with minimal hardware requirements. Intensity images are captured with different source patterns and a non-linear phase retrieval optimization reconstructs…
Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference. However, their practical runtime usually lags behind the theoretical…
Image segmentation techniques are predominately based on parameter-laden optimization. The objective function typically involves weights for balancing competing image fidelity and segmentation regularization cost terms. Setting these…
Deep neural networks are typically trained by optimizing a loss function with an SGD variant, in conjunction with a decaying learning rate, until convergence. We show that simple averaging of multiple points along the trajectory of SGD,…
Spectral algorithms leverage spectral regularization techniques to analyze and process data, providing a flexible framework for addressing supervised learning problems. To deepen our understanding of their performance in real-world…