Improving Translation Invariance in Convolutional Neural Networks with Peripheral Prediction Padding

2023/07/15 by Kensuke Mukai, Mukai, Kensuke, Takao Yamanaka +1 · 1 citation
Computer Science · #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Hand Gesture Recognition Systems #Human Pose and Action Recognition

paper · pdf · doi:10.48550/arxiv.2307.07725

openalex publication_date 2023/07/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Zero padding is often used in convolutional neural networks to prevent the feature map size from decreasing with each layer. However, recent studies have shown that zero padding promotes encoding of absolute positional information, which may adversely affect the performance of some tasks. In this work, a novel padding method called Peripheral Prediction Padding (PP-Pad) method is proposed, which enables end-to-end training of padding values suitable for each task instead of zero padding. Moreover, novel metrics to quantitatively evaluate the translation invariance of the model are presented. By evaluating with these metrics, it was confirmed that the proposed method achieved higher accuracy and translation invariance than the previous methods in a semantic segmentation task.

Cited by

• Refined Modeling of Arctic Circumpolar Building Stock Increases Estimated Mid‐Century Permafrost Degradation Damages

Related

• Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features
• Position, Padding and Predictions: A Deeper Look at Position Information in CNNs
• Partial Convolution based Padding
• Deep Convolutional Neural Networks with Zero-Padding: Feature Extraction and Learning
• Towards Closing the Gap in Weakly Supervised Semantic Segmentation with DCNNs: Combining Local and Global Models