Loading [a11y]/accessibility-menu.js
RC-CNN: Representation-Consistent Convolutional Neural Networks for Achieving Transformation Invariance | IEEE Conference Publication | IEEE Xplore

RC-CNN: Representation-Consistent Convolutional Neural Networks for Achieving Transformation Invariance


Abstract:

Convolutional neural networks (CNNs) are powerful and have achieved state-of-the-art performance in many visual recognition tasks. Despite their impressive performance, C...Show More

Abstract:

Convolutional neural networks (CNNs) are powerful and have achieved state-of-the-art performance in many visual recognition tasks. Despite their impressive performance, CNNs are still unable to remain invariant while some spatial transformations are applied on images. Herein, we propose representation-consistent neural networks to solve this problem. By introducing consistent losses between the representations in different layers of transformed images, the recognition performance of transformed images is significantly improved. This model not only learns to map from the transformed images to the pre-defined labels but each layer also learns to generate invariant representations when the input images are transformed. All the characteristics of transformation invariance are embedded in the model, which means that no extra parameters or computations are introduced in the well-trained model. Comparative experiments demonstrate the superiority of our model when learning invariance to rotation, translation, and scaling on large-scale image recognition and retrieval tasks.
Date of Conference: 06-09 October 2019
Date Added to IEEE Xplore: 28 November 2019
ISBN Information:

ISSN Information:

Conference Location: Bari, Italy

References

References is not available for this document.