Adapted Center and Scale Prediction: More Stable and More Accurate

2020-02-20 · Wenhao Wang

Pedestrian detection benefits from deep learning technology and gains rapid development in recent years. Most of detectors follow general object detection frame, i.e. default boxes and two-stage process. Recently, anchor-free and one-stage detectors have been introduced into this area. However, their accuracies are unsatisfactory. Therefore, in order to enjoy the simplicity of anchor-free detectors and the accuracy of two-stage ones simultaneously, we propose some adaptations based on a detector, Center and Scale Prediction(CSP). The main contributions of our paper are: (1) We improve the robustness of CSP and make it easier to train. (2) We propose a novel method to predict width, namely compressing width. (3) We achieve the second best performance on CityPersons benchmark, i.e. 9.3% log-average miss rate(MR) on reasonable set, 8.7% MR on partial set and 5.6% MR on bare set, which shows an anchor-free and one-stage detector can still have high accuracy. (4) We explore some capabilities of Switchable Normalization which are not mentioned in its original paper.

📄 PDF Abstract BibTeX arXiv:2002.09053

Code (1)

WangWenhao0716/Adapted-Center-and-Scale-Prediction pytorch

Tasks

object-detection Object Detection Pedestrian Detection

Methods 이 논문이 사용한 방법론

Instance Normalization Instance Normalization (also known as contrast normalization) is a normalization layer where: $$ y_{tijk} = \frac{x_{tijk} - \mu_{ti}}{\sqrt{\sigma_{ti}^2 +…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Batch Normalization 설명 없음

Switchable Normalization 설명 없음

A note and a correction on measuring cognitive distance in multiple dimensions

2016-07-15 · Rousseau Ronald, Rahman A. I. M. Jakaria, Guns Raf, Engels Tim C. E.

In a previous article (Rahman, Guns, Rousseau, and Engels, 2015) we described several approaches to determine the cognitive distance between two units. One of these approaches was based on what we called barycenters in N…

SCALE:Scalable Conditional Atlas-Level Endpoint transport for virtual cell perturbation prediction

2026-03-18 · Shuizhou Chen, Lang Yu, Kedu Jin, Songming Zhang 외 arxiv

Virtual cell models aim to enable in silico experimentation by predicting how cells respond to genetic, chemical, or cytokine perturbations from single-cell measurements. In practice, however, large-scale perturbation pr…

Heart2Mind: Human-Centered Contestable Psychiatric Disorder Diagnosis System using Wearable ECG Monitors

2025-05-16 · Hung Nguyen, Alireza Rahimi, Veronica Whitford, Hélène Fournier 외

Psychiatric disorders affect millions globally, yet their diagnosis faces significant challenges in clinical practice due to subjective assessments and accessibility concerns, leading to potential delays in treatment. To…

Explainable artificial intelligence Explainable Artificial Intelligence (XAI)Heart Rate Variability Time Series

Gaze Distribution Analysis and Saliency Prediction Across Age Groups

2017-05-20 · Onkar Krishna, Kiyoharu Aizawa, Andrea Helo, Rama Pia

Knowledge of the human visual system helps to develop better computational models of visual attention. State-of-the-art models have been developed to mimic the visual attention system of young adults that, however, large…

Prediction Saliency Prediction

GigaWorld-Policy: An Efficient Action-Centered World--Action Model

2026-03-18 · Angen Ye, Boyuan Wang, Chaojun Ni, Guan Huang 외 arxiv

World-Action Models (WAM) initialized from pre-trained video generation backbones have demonstrated remarkable potential for robot policy learning. However, existing approaches face two critical bottlenecks that hinder p…

Video Generation