Improving Content-Invariance in Gated Autoencoders for 2D and 3D Object Rotation
Content-invariance in mapping codes learned by GAEs is a useful feature for various relation learning tasks. In this paper we show that the content-invariance of mapping codes for images of 2D and 3D rotated objects can be substantially improved by extending the standard GAE loss (symmetric reconstruction error) with a regularization term that penalizes the symmetric cross-reconstruction error. This error term involves reconstruction of pairs with mapping codes obtained from other pairs exhibiting similar transformations. Although this would principally require knowledge of the transformations exhibited by training pairs, our experiments show that a bootstrapping approach can sidestep this issue, and that the regularization term can effectively be used in an unsupervised setting.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Endowing Deep 3D Models with Rotation Invariance Based on Principal Component Analysis
In this paper, we propose a simple yet effective method to endow deep 3D models with rotation invariance by expressing the coordinates in an intrinsic frame determined by the object shape itself. Key to our approach is t…
ObjectRetrievalPatch Reordering: a Novel Way to Achieve Rotation and Translation Invariance in Convolutional Neural Networks
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 lo…
Data AugmentationImage RetrievalRetrievalTranslationHFBRI-MAE: Handcrafted Feature Based Rotation-Invariant Masked Autoencoder for 3D Point Cloud Analysis
Self-supervised learning (SSL) has demonstrated remarkable success in 3D point cloud analysis, particularly through masked autoencoders (MAEs). However, existing MAE-based methods lack rotation invariance, leading to sig…
Few-Shot LearningSelf-Supervised LearningTheta-RBM: Unfactored Gated Restricted Boltzmann Machine for Rotation-Invariant Representations
Learning invariant representations is a critical task in computer vision. In this paper, we propose the Theta-Restricted Boltzmann Machine ({\theta}-RBM in short), which builds upon the original RBM formulation and injec…
Towards Rotation Invariance in Object Detection
Rotation augmentations generally improve a model's invariance/equivariance to rotation - except in object detection. In object detection the shape is not known, therefore rotation creates a label ambiguity. We show that …
Objectobject-detectionObject Detection