相关论文: Adaptive Patch Exiting for Scalable Single Image S…

This paper proposes an adaptive neural-compilation framework to address the problem of efficient program learning. Traditional code optimisation strategies used in compilers are based on applying pre-specified set of transformations that…

Adversarial training (AT) with projected gradient descent is the most popular method to improve model robustness under adversarial attacks. However, computational overheads become prohibitively large when AT is applied to large backbone…

The progressive hedging algorithm (PHA) is a cornerstone among algorithms for large-scale stochastic programming problems. However, its traditional implementation is hindered by some limitations, including the requirement to solve all…

High-performance object detection relies on expensive convolutional networks to compute features, often leading to significant challenges in applications, e.g. those that require detecting objects from video streams in real time. The key to…

In this paper, we propose an adaptive sieving (AS) strategy for solving general sparse machine learning models by effectively exploring the intrinsic sparsity of the solutions, wherein only a sequence of reduced problems with much smaller…

This paper introduces an efficient sparse recovery approach for Polynomial Chaos (PC) expansions, which promotes the sparsity by breaking the dimensionality of the problem. The proposed algorithm incrementally explores sub-dimensional…

Flexibility at hardware level is the main driving force behind adaptive systems whose aim is to realise microarhitecture deconfiguration 'online'. This feature allows the software/hardware stack to tolerate drastic changes of the workload…

Stereo Depth Estimation (SDE) is essential for scene perception in vision-based systems such as autonomous driving. Prior work shows SDE is vulnerable to pixel-optimization attacks, but these methods are limited to digital, static, and…

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…

We investigate the robustness of sparse artificial neural networks trained with adaptive topology. We focus on a simple yet effective architecture consisting of three sparse layers with 99% sparsity followed by a dense layer, applied to…

Deep-learning accelerators are increasingly in demand; however, their performance is constrained by the size of the feature map, leading to high bandwidth requirements and large buffer sizes. We propose an adaptive scale feature map…

Imposing known physical constraints, such as conservation laws, during neural network training introduces an inductive bias that can improve accuracy, reliability, convergence, and data efficiency for modeling physical dynamics. While such…

The goal of this paper is to present a new efficient image segmentation method based on evolutionary computation which is a model inspired from human behavior. Based on this model, a four layer process for image segmentation is proposed…

Multi-channel keyword spotting (KWS) has become crucial for voice-based applications in edge environments. However, its substantial computational and energy requirements pose significant challenges. We introduce ASAP-FE (Agile…

Sparse neural networks are a key factor in developing resource-efficient machine learning applications. We propose the novel and powerful sparse learning method Adaptive Regularized Training (ART) to compress dense into sparse networks.…

Existing methods for image alignment struggle in cases involving feature-sparse regions, extreme scale and field-of-view differences, and large deformations, often resulting in suboptimal accuracy. Robustness to these challenges can be…

Synchronization overheads pose a major challenge as applications advance towards extreme scales. In current large-scale algorithms, synchronization as well as data communication delay the parallel computations at each time step in a…

Deep learning based methods have recently pushed the state-of-the-art on the problem of Single Image Super-Resolution (SISR). In this work, we revisit the more traditional interpolation-based methods, that were popular before, now with the…

Image superresolution involves the processing of an image sequence to generate a still image with higher resolution. Classical approaches, such as bayesian MAP methods, require iterative minimization procedures, with high computational…

We propose a general method to train a single convolutional neural network which is capable of switching image resolutions at inference. Thus the running speed can be selected to meet various computational resource limits. Networks trained…