Related papers: AdaBM: On-the-Fly Adaptive Bit Mapping for Image S…
With the development of high-definition display devices, the practical scenario of Super-Resolution (SR) usually needs to super-resolve large input like 2K to higher resolution (4K/8K). To reduce the computational and memory cost, current…
Although numerous solutions have been proposed for image super-resolution, they are usually incompatible with low-power devices with many computational and memory constraints. In this paper, we address this problem by proposing a simple yet…
Conventional model quantization methods use a fixed quantization scheme to different data samples, which ignores the inherent "recognition difficulty" differences between various samples. We propose to feed different data samples with…
The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-frequency regions (e.g., edges and textures) are most critical…
Recent years have witnessed tremendous progress in single image super-resolution (SISR) owing to the deployment of deep convolutional neural networks (CNNs). For most existing methods, the computational cost of each SISR model is irrelevant…
Despite breakthrough advances in image super-resolution (SR) with convolutional neural networks (CNNs), SR has yet to enjoy ubiquitous applications due to the high computational complexity of SR networks. Quantization is one of the…
Although deep learning models are highly effective for various learning tasks, their high computational costs prohibit the deployment to scenarios where either memory or computational resources are limited. In this paper, we focus on…
Deep neural networks with adaptive configurations have gained increasing attention due to the instant and flexible deployment of these models on platforms with different resource budgets. In this paper, we investigate a novel option to…
Multi-bit spiking neural networks (SNNs) have recently become a heated research spot, pursuing energy-efficient and high-accurate AI. However, with more bits involved, the associated memory and computation demands escalate to the point…
Normalization like Batch Normalization (BN) is a milestone technique to normalize the distributions of intermediate layers in deep learning, enabling faster training and better generalization accuracy. However, in fidelity image…
Large-scale deep neural networks (DNNs) have achieved remarkable success in many application scenarios. However, high computational complexity and energy costs of modern DNNs make their deployment on edge devices challenging. Model…
Low-bit quantization is widely used to compress super-resolution (SR) models and reduce storage and computation costs for deployment on resource-limited devices. However, when SR models are pushed to ultra-low precision (2-4 bits),…
This paper proposes an Any-time super-Resolution Method (ARM) to tackle the over-parameterized single image super-resolution (SISR) models. Our ARM is motivated by three observations: (1) The performance of different image patches varies…
This paper introduces the notion of soft bits to address the rate-distortion optimization for learning-based image compression. Recent methods for such compression train an autoencoder end-to-end with an objective to strike a balance…
This paper addresses the challenges of storage and communication costs for large-scale datasets in resource-constrained edge devices by proposing a novel dataset quantization approach to reduce intra-sample redundancy. Unlike traditional…
In this paper, we explore a novel image matting task aimed at achieving efficient inference under various computational cost constraints, specifically FLOP limitations, using a single matting network. Existing matting methods which have not…
Quantizing deep networks with adaptive bit-widths is a promising technique for efficient inference across many devices and resource constraints. In contrast to static methods that repeat the quantization process and train different models…
Physical systems commonly exhibit spatially varying complexity, presenting a significant challenge for neural PDE solvers. While Graph Neural Networks can handle the irregular meshes required for complex geometries and boundary conditions,…
Deep neural networks have achieved remarkable success in single image super-resolution (SISR). The computing and memory requirements of these methods have hindered their application to broad classes of real devices with limited computing…
Most single image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs, which are simulated by a predetermined degradation operation, e.g., bicubic downsampling. However, these…