[2010.07621] HS-ResNet: Hierarchical-Split Block on Convolutional Neural Networkopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

This paper addresses representational block named Hierarchical-Split Block, which can be taken as a plug-and-play block to upgrade existing convolutional neural networks, improves model performance significantly in a network. Hierarchical-Split Block contains many hierarchical split and concatenate connections within one single residual block. We find multi-scale features is of great importance for numerous vision tasks. Moreover, Hierarchical-Split block is very flexible and efficient, which provides a large space of potential network architectures for different applications. In this work, we present a common backbone based on Hierarchical-Split block for tasks: image classification, object detection, instance segmentation and semantic image segmentation/parsing. Our approach shows significant improvements over all these core tasks in comparison with the baseline. As shown in Figure1, for image classification, our 50-layers network(HS-ResNet50) achieves 81.28% top-1 accuracy with comp

1 mentions: @arxiv_cs_cv_pr
Date: 2020/10/16 03:51

Related Entries

Read more [1910.10328] Iterative Matching Point
0 users, 2 mentions 2019/10/24 14:20
Read more [2002.08721] A survey on Semi-, Self- and Unsupervised Techniques in Image Classificationcontact arX...
0 users, 1 mentions 2020/02/21 06:51
Read more [2005.03846] Synchronous Bidirectional Learning for Multilingual Lip Readingopen searchopen navigati...
0 users, 1 mentions 2020/05/13 23:21
Read more [2008.05667] Feature Binding with Category-Dependant MixUp for Semantic Segmentation and Adversarial...
0 users, 1 mentions 2020/08/14 02:21
Read more [2009.08899] Image Captioning with Attention for Smart Local Tourism using EfficientNetopen searchop...
0 users, 1 mentions 2020/09/21 02:21