paper-with-me

홈 › Papers

Understanding the Ability of Deep Neural Networks to Count Connected Components in Images

2021-01-05 · Shuyue Guan, Murray Loew

Humans can count very fast by subitizing, but slow substantially as the number of objects increases. Previous studies have shown a trained deep neural network (DNN) detector can count the number of objects in an amount of time that increases slowly with the number of objects. Such a phenomenon suggests the subitizing ability of DNNs, and unlike humans, it works equally well for large numbers. Many existing studies have successfully applied DNNs to object counting, but few studies have studied the subitizing ability of DNNs and its interpretation. In this paper, we found DNNs do not have the ability to generally count connected components. We provided experiments to support our conclusions and explanations to understand the results and phenomena of these experiments. We proposed three ML-learnable characteristics to verify learnable problems for ML models, such as DNNs, and explain why DNNs work for specific counting problems but cannot generally count connected components.

📄 PDF Abstract BibTeX arXiv:2101.01386

Code (0)

등록된 구현이 없습니다.

Tasks

Object Counting

Similar Papers 제목 키워드 기반

P-Count: Persistence-based Counting of White Matter Hyperintensities in Brain MRI

2024-03-20 · Xiaoling Hu, Annabel Sorby-Adams, Frederik Barkhof, W Taylor Kimberly 외

White matter hyperintensities (WMH) are a hallmark of cerebrovascular disease and multiple sclerosis. Automated WMH segmentation methods enable quantitative analysis via estimation of total lesion load, spatial distribut…

Lesion SegmentationSegmentation

Number of Connected Components in a Graph: Estimation via Counting Patterns

2018-12-01 · Ashish Khetan, Harshay Shah, Sewoong Oh

Due to the limited resources and the scale of the graphs in modern datasets, we often get to observe a sampled subgraph of a larger original graph of interest, whether it is the worldwide web that has been crawled or soc…

Understanding Mode Connectivity via Parameter Space Symmetry

2025-05-29 · Bo Zhao, Nima Dehmamy, Robin Walters, Rose Yu

Neural network minima are often connected by curves along which train and test loss remain nearly constant, a phenomenon known as mode connectivity. While this property has enabled applications such as model merging and …

Linear Mode Connectivity

Segmentação e contagem de troncos de madeira utilizando deep learning e processamento de imagens

2023-08-31 · João V. C. Mazzochin, Gustavo Tiecker, Erick O. Rodrigues

Counting objects in images is a pattern recognition problem that focuses on identifying an element to determine its incidence and is approached in the literature as Visual Object Counting (VOC). In this work, we propose …

Object CountingSegmentation

Deep Reinforcement Learning in Lane Merge Coordination for Connected Vehicles

2020-10-20 · Omar Nassef, Luis Sequeira, Elias Salam, Toktam Mahmoodi

In this paper, a framework for lane merge coordination is presented utilising a centralised system, for connected vehicles. The delivery of trajectory recommendations to the connected vehicles on the road is based on a T…

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)