paper-with-me

Papers

Self-Normalized Density Map (SNDM) for Counting Microbiological Objects

2022-03-15 · Krzysztof M. Graczyk, Jaroslaw Pawlowski, Sylwia Majchrowska, Tomasz Golan

The statistical properties of the density map (DM) approach to counting microbiological objects on images are studied in detail. The DM is given by U$^2$-Net. Two statistical methods for deep neural networks are utilized: the bootstrap and the Monte Carlo (MC) dropout. The detailed analysis of the uncertainties for the DM predictions leads to a deeper understanding of the DM model's deficiencies. Based on our investigation, we propose a self-normalization module in the network. The improved network model, called \textit{Self-Normalized Density Map} (SNDM), can correct its output density map by itself to accurately predict the total number of objects in the image. The SNDM architecture outperforms the original model. Moreover, both statistical frameworks -- bootstrap and MC dropout -- have consistent statistical results for SNDM, which were not observed in the original model. The SNDM efficiency is comparable with the detector-base models, such as Faster and Cascade R-CNN detectors.

📄 PDF Abstract BibTeX arXiv:2203.09474

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Cascade R-CNN Cascade R-CNN is an object detection architecture that seeks to address problems with degrading performance with increased IoU thresholds (due to overfitting during training…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

A Dense Siamese U-Net trained with Edge Enhanced 3D IOU Loss for Image Co-segmentation

2021-08-17 · Xi Liu, Xiabi Liu, Huiyu Li, Xiaopeng Gong

Image co-segmentation has attracted a lot of attentions in computer vision community. In this paper, we propose a new approach to image co-segmentation through introducing the dense connections into the decoder path of S…

DecoderSegmentation

Learn to Scale: Generating Multipolar Normalized Density Maps for Crowd Counting

2019-07-29 · ICCV 2019 10 · Chenfeng Xu, Kai Qiu, Jianlong Fu, Song Bai 외

Dense crowd counting aims to predict thousands of human instances from an image, by calculating integrals of a density map over image pixels. Existing approaches mainly suffer from the extreme density variances. Such den…

Crowd CountingDensity Estimation

Distribution Matching for Crowd Counting

2020-09-28 · NeurIPS 2020 12 · Boyu Wang, Huidong Liu, Dimitris Samaras, Minh Hoai

In crowd counting, each training image contains multiple people, where each person is annotated by a dot. Existing crowd counting methods need to use a Gaussian to smooth each annotated dot or to estimate the likelihood …

Crowd Counting

DSNDM: Deep Siamese Neural Discourse Model with Attention for Text Pairs Categorization and Ranking

2020-11-01 · EMNLP (CODI) 2020 11 · Alexander Chernyavskiy, Dmitry Ilvovsky

In this paper, the utility and advantages of the discourse analysis for text pairs categorization and ranking are investigated. We consider two tasks in which discourse structure seems useful and important: automatic ver…

Question Answering

A Comparison of Bacterial Colonies Count from Petri Dishes Utilizing Hough Transform and Traditional Manual Counting

2025-05-26 · Areesha Rehman, Zikria Saleem, Jarrar Amjad, Syed Rehan Shah 외

Bacterial colony enumeration is an essential stage in microbiological research, allowing susceptibility to antibiotics assessment, monitoring of the environment, and clinical diagnostics. Traditional manual counting meth…