Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition

TL;DR

This paper introduces pyramidal convolution (PyConv), a multi-scale, efficient convolutional approach that enhances visual recognition tasks without increasing computational costs, demonstrating significant improvements across various computer vision benchmarks.

Contribution

PyConv is a novel multi-scale convolutional method that captures different scene details efficiently, enabling improved performance across multiple visual recognition tasks.

Findings

Outperforms ResNet-152 on ImageNet with fewer parameters and lower complexity.

Sets new state-of-the-art on ADE20K scene parsing benchmark.

Achieves significant improvements in image classification, detection, and segmentation tasks.

Abstract

This work introduces pyramidal convolution (PyConv), which is capable of processing the input at multiple filter scales. PyConv contains a pyramid of kernels, where each level involves different types of filters with varying size and depth, which are able to capture different levels of details in the scene. On top of these improved recognition capabilities, PyConv is also efficient and, with our formulation, it does not increase the computational cost and parameters compared to standard convolution. Moreover, it is very flexible and extensible, providing a large space of potential network architectures for different applications. PyConv has the potential to impact nearly every computer vision task and, in this work, we present different architectures based on PyConv for four main tasks on visual recognition: image classification, video action classification/recognition, object detection and semantic image segmentation/parsing. Our approach shows significant improvements over all these core tasks in comparison with the baselines. For instance, on image recognition, our 50-layers network outperforms in terms of recognition performance on ImageNet dataset its counterpart baseline ResNet with 152 layers, while having 2.39 times less parameters, 2.52 times lower computational complexity and more than 3 times less layers. On image segmentation, our novel framework sets a new state-of-the-art on the challenging ADE20K benchmark for scene parsing. Code is available at: https://github.com/iduta/pyconv