Patch Reordering: A Novel Way To Achieve Rotation And Translation Invariance In Convolutional Neural Networks

Abstract

Convolutional Neural Networks (CNNs) have demonstrated state-of-the-art performance on many visual recognition tasks. However, the combination of convolution and pooling operations only shows invariance to small local location changes in meaningful objects in input. Sometimes, such networks are trained using data augmentation to encode this invariance into the parameters, which restricts the capacity of the model to learn the content of these objects. A more efficient use of the parameter budget is to encode rotation or translation invariance into the model architecture, which relieves the model from the need to learn them. To enable the model to focus on learning the content of objects other than their locations, we propose to conduct patch ranking of the feature maps before feeding them into the next layer. When patch ranking is combined with convolution and pooling operations, we obtain consistent representations despite the location of meaningful objects in input. We show that the

Stats

• citations1
• S2 citations—
• github stars13
• HF likes0
• heat score4.55
• arxiv keyshen2019patch

Related papers

• Transform-invariant Convolutional Neural Networks For Image Classification And Search (2019)13.58
• Convolutional Patch Representations For Image Retrieval: An Unsupervised Approach (2016)12.47
• Compensating For Large In-plane Rotations In Natural Images (2016)6.34
• Group Invariant Deep Representations For Image Instance Retrieval (2016)0.00
• Rotation Invariant Deep CBIR (2020)0.00
• Reuse Your Features: Unifying Retrieval And Feature-metric Alignment (2022)1.69
• Patch-wise Retrieval: A Bag Of Practical Techniques For Instance-level Matching (2025)0.00
• Two-stage Discriminative Re-ranking For Large-scale Landmark Retrieval (2020)15.20