This paper reviews the NTIRE 2024 challenge on image super-resolution (x4) highlighting
the solutions proposed and the outcomes obtained. The challenge involves generating …

This paper reviews the NTIRE 2023 challenge on efficient single-image super-resolution
with a focus on the proposed solutions and results. The aim of this challenge is to devise a …

Real-time object detection is one of the most important research topics in computer vision.
As new approaches regarding architecture optimization and training optimization are …

We revisit large kernel design in modern convolutional neural networks (CNNs). Inspired by
recent advances in vision transformers (ViTs), in this paper, we demonstrate that using a few …

Abstract Recently lightweight Vision Transformers (ViTs) demonstrate superior performance
and lower latency compared with lightweight Convolutional Neural Networks (CNNs) on …

Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source
domain (eg synthetic data) to the target domain (eg real-world data) without requiring further …

The recent amalgamation of transformer and convolutional designs has led to steady
improvements in accuracy and efficiency of the models. In this work, we introduce FastViT, a …

Efficient neural network backbones for mobile devices are often optimized for metrics such
as FLOPs or parameter count. However, these metrics may not correlate well with latency of …

We present a simple but powerful architecture of convolutional neural network, which has a
VGG-like inference-time body composed of nothing but a stack of 3x3 convolution and …

State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the
point clouds to 2D space and then process them via 2D convolution. Although this …