Rotation invariant CNN using scattering transform for image classification
원문 초록
Deep convolutional neural networks accuracy is heavily impacted by rotations of the input data. In this paper, we propose a convolutional predictor that is invariant to rotations in the input. This architecture is capable of predicting the angular orientation without angle-annotated data. Furthermore, the predictor maps continuously the random rotation of the input to a circular space of the prediction. For this purpose, we use the roto-translation properties existing in the Scattering Transform Networks with a series of 3D Convolutions. We validate the results by training with upright and randomly rotated samples. This allows further applications of this work on fields like automatic re-orientation of randomly oriented datasets.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
One Prototype Is Enough: Single-Prototype Activation for Interpretable Image Classification
Hyperspectral Image Classification via Transformer-based Spectral-Spatial Attention Decoupling and Adaptive Gating
Adversarial attacks to image classification systems using evolutionary algorithms
Disentangled representations of microscopy images
SIM-Net: A Multimodal Fusion Network Using Inferred 3D Object Shape Point Clouds from RGB Images for 2D Classification
FedWSIDD: Federated Whole Slide Image Classification via Dataset Distillation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.