Related papers: Rethinking Bottleneck Structure for Efficient Mobi…

A residual-networks family with hundreds or even thousands of layers dominates major image recognition tasks, but building a network by simply stacking residual blocks inevitably limits its optimization ability. This paper proposes a novel…

We propose a novel neural architecture for computer vision -- WaveMix -- that is resource-efficient and yet generalizable and scalable. While using fewer trainable parameters, GPU RAM, and computations, WaveMix networks achieve comparable…

The display devices like HDR10 televisions are increasingly prevalent in our daily life for visualizing high dynamic range (HDR) images. But the majority of media images on the internet remain in 8-bit standard dynamic range (SDR) format.…

A generalization of modularity, called block modularity, is defined. This is a quality function which evaluates a label assignment against an arbitrary block pattern. Therefore, unlike standard modularity or its variants, arbitrary network…

We present the next generation of MobileNets based on a combination of complementary search techniques as well as a novel architecture design. MobileNetV3 is tuned to mobile phone CPUs through a combination of hardware-aware network…

A hallmark of chaotic dynamics is the loss of information with time. Although information loss is often expressed through a connection to Lyapunov exponents -- valid in the limit of high information about the system state -- this picture…

Shuffling strategies for stochastic gradient descent (SGD), including incremental gradient, shuffle-once, and random reshuffling, are supported by rigorous convergence analyses for arbitrary within-epoch permutations. In particular, random…

Learned inverse problem solvers exhibit remarkable performance in applications like image reconstruction tasks. These data-driven reconstruction methods often follow a two-step scheme. First, one trains the often neural network-based…

Residual learning is a recently proposed learning framework to facilitate the training of very deep neural networks. Residual blocks or units are made of a set of stacked layers, where the inputs are added back to their outputs with the aim…

Despite recent progress in our understanding of complex dynamic networks, it remains challenging to devisesufficiently accurate models to observe, control or predict the state of real systems in biology, economics or other fields. A largely…

Remote sensing segmentation has a wide range of applications in environmental protection, and urban change detection, etc. Despite the success of deep learning-based remote sensing segmentation methods (e.g., CNN and Transformer), they are…

\textit{Differentiable ARchiTecture Search} (DARTS) has recently become the mainstream of neural architecture search (NAS) due to its efficiency and simplicity. With a gradient-based bi-level optimization, DARTS alternately optimizes the…

Microstructural materials design is one of the most important applications of inverse modeling in materials science. Generally speaking, there are two broad modeling paradigms in scientific applications: forward and inverse. While the…

Effective adaptation to distribution shifts in training data is pivotal for sustaining robustness in neural networks, especially when removing specific biases or outdated information, a process known as machine unlearning. Traditional…

The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex…

Mobile wireless networks are intrinsically more prone to link congestion and outright failures than wired networks. In this paper, we elaborate the resilient routing reconfiguration method of \cite{WangEtAl} and generalize it to accomodate…

SegBlocks reduces the computational cost of existing neural networks, by dynamically adjusting the processing resolution of image regions based on their complexity. Our method splits an image into blocks and downsamples blocks of low…

Image rescaling is a commonly used bidirectional operation, which first downscales high-resolution images to fit various display screens or to be storage- and bandwidth-friendly, and afterward upscales the corresponding low-resolution…

Secret information sharing through image carrier has aroused much research attention in recent years with images' growing domination on the Internet and mobile applications. However, with the booming trend of convolutional neural networks,…

Recently, Neural architecture search has achieved great success on classification tasks for mobile devices. The backbone network for object detection is usually obtained on the image classification task. However, the architecture which is…