paper-with-me

홈 › Papers

Bioinspired CNNs for border completion in occluded images

2026-03-11 · Catarina P. Coutinho, Aneeqa Merhab, Janko Petkovic, Ferdinando Zanchetta, Rita Fioresi arxiv

We exploit the mathematical modeling of the border completion problem in the visual cortex to design convolutional neural network (CNN) filters that enhance robustness to image occlusions. We evaluate our CNN architecture, BorderNet, on three occluded datasets (MNIST, Fashion-MNIST, and EMNIST) under two types of occlusions: stripes and grids. In all cases, BorderNet demonstrates improved performance, with gains varying depending on the severity of the occlusions and the dataset.

📄 PDF Abstract BibTeX arXiv:2603.10694

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

BIFRNet: A Brain-Inspired Feature Restoration DNN for Partially Occluded Image Recognition

2023-03-02 · Jiahong Zhang, Lihong Cao, Qiuxia Lai, Binyao Li 외

The partially occluded image recognition (POIR) problem has been a challenge for artificial intelligence for a long time. A common strategy to handle the POIR problem is using the non-occluded features for classification…

Feature Completion for Occluded Person Re-Identification

2021-06-24 · Ruibing Hou, Bingpeng Ma, Hong Chang, Xinqian Gu 외

Person re-identification (reID) plays an important role in computer vision. However, existing methods suffer from performance degradation in occluded scenes. In this work, we propose an occlusion-robust block, Region Fea…

DecoderOccluded Person Re-IdentificationPerson Re-Identification

Semantic Point Completion Network for 3D Semantic Scene Completion

2020-08-29 · ECAI 2020 8 · Min Zhong, Gang Zeng

Semantic scene completion (SSC) is composed of scene completion (SC) and semantic segmentation. Most of the existing methods carry out SSC in a regular 3D grid space, where 3D CNNs cause unnecessary computational cost…

3D Semantic Scene CompletionDecoderSemantic Segmentation

Feature Completion Transformer for Occluded Person Re-identification

2023-03-03 · Tao Wang, Mengyuan Liu, Hong Liu, Wenhao Li 외

Occluded person re-identification (Re-ID) is a challenging problem due to the destruction of occluders. Most existing methods focus on visible human body parts through some prior information. However, when complementary …

Occluded Person Re-IdentificationPerson Re-IdentificationTriplet

Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion

2020-03-10 · CVPR 2020 6 · Adam Kortylewski, Ju He, Qing Liu, Alan Yuille

Recent findings show that deep convolutional neural networks (DCNNs) do not generalize well under partial occlusion. Inspired by the success of compositional models at classifying partially occluded objects, we propose t…

General Classification