paper-with-me

Papers

BEA: Revisiting anchor-based object detection DNN using Budding Ensemble Architecture

2023-09-14 · Syed Sha Qutub, Neslihan Kose, Rafael Rosales, Michael Paulitsch, Korbinian Hagn, Florian Geissler, Yang Peng, Gereon Hinz, Alois Knoll

This paper introduces the Budding Ensemble Architecture (BEA), a novel reduced ensemble architecture for anchor-based object detection models. Object detection models are crucial in vision-based tasks, particularly in autonomous systems. They should provide precise bounding box detections while also calibrating their predicted confidence scores, leading to higher-quality uncertainty estimates. However, current models may make erroneous decisions due to false positives receiving high scores or true positives being discarded due to low scores. BEA aims to address these issues. The proposed loss functions in BEA improve the confidence score calibration and lower the uncertainty error, which results in a better distinction of true and false positives and, eventually, higher accuracy of the object detection models. Both Base-YOLOv3 and SSD models were enhanced using the BEA method and its proposed loss functions. The BEA on Base-YOLOv3 trained on the KITTI dataset results in a 6% and 3.7% increase in mAP and AP50, respectively. Utilizing a well-balanced uncertainty estimation threshold to discard samples in real-time even leads to a 9.6% higher AP50 than its base model. This is attributed to a 40% increase in the area under the AP50-based retention curve used to measure the quality of calibration of confidence scores. Furthermore, BEA-YOLOV3 trained on KITTI provides superior out-of-distribution detection on Citypersons, BDD100K, and COCO datasets compared to the ensembles and vanilla models of YOLOv3 and Gaussian-YOLOv3.

📄 PDF Abstract BibTeX arXiv:2309.08036

Code (0)

등록된 구현이 없습니다.

Tasks

2D Object Detectionobject-detectionObject DetectionOut-of-Distribution Detection

Methods 이 논문이 사용한 방법론

BNB Customer Service Number +1-833-534-1729 설명 없음
Average Pooling 설명 없음
Residual Connection 설명 없음
Batch Normalization 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
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 $x$…
Logistic Regression Logistic Regression, despite its name, is a linear model for classification rather than regression. Logistic regression is also known in the literature as logit regression,…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Situation Monitor: Diversity-Driven Zero-Shot Out-of-Distribution Detection using Budding Ensemble Architecture for Object Detection

2024-06-05 · Qutub Syed, Michael Paulitsch, Korbinian Hagn, Neslihan Kose Cihangir 외

We introduce Situation Monitor, a novel zero-shot Out-of-Distribution (OOD) detection approach for transformer-based object detection models to enhance reliability in safety-critical machine learning applications such as…

Autonomous DrivingDiversityobject-detectionObject Detection+2

Revisiting Feature Alignment for One-stage Object Detection

2019-08-05 · Yuntao Chen, Chenxia Han, Naiyan Wang, Zhao-Xiang Zhang

Recently, one-stage object detectors gain much attention due to their simplicity in practice. Its fully convolutional nature greatly reduces the difficulty of training and deployment compared with two-stage detectors whi…

Objectobject-detectionObject Detection

Enhancing Object Detection for Autonomous Driving by Optimizing Anchor Generation and Addressing Class Imbalance

2021-04-08 · Manuel Carranza-García, Pedro Lara-Benítez, Jorge García-Gutiérrez, José C. Riquelme

Object detection has been one of the most active topics in computer vision for the past years. Recent works have mainly focused on pushing the state-of-the-art in the general-purpose COCO benchmark. However, the use of s…

Autonomous DrivingAutonomous VehiclesEvolutionary Algorithmsobject-detection+1

Revisiting the Loss Weight Adjustment in Object Detection

2021-03-17 · Wenxin Yu, Xueling Shen, Jiajie Hu, Dong Yin

Object detection is a typical multi-task learning application, which optimizes classification and regression simultaneously. However, classification loss always dominates the multi-task loss in anchor-based methods, hamp…

ClassificationGeneral ClassificationMulti-Task LearningObject+3

Ensemble YOLO Framework for Multi-Domain Mitotic Figure Detection in Histopathology Images

2025-09-03 · Navya Sri Kelam, Akash Parekh, Saikiran Bonthu, Nitin Singhal arxiv

The reliable identification of mitotic figures in whole-slide histopathological images remains difficult, owing to their low prevalence, substantial morphological heterogeneity, and the inconsistencies introduced by tiss…