CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection

2020-03-07 · Bin Zhu, Qing Song, Lu Yang, Zhihui Wang, Chun Liu, Mengjie Hu

In object detection, offset-guided and point-guided regression dominate anchor-based and anchor-free method separately. Recently, point-guided approach is introduced to anchor-based method. However, we observe points predicted by this way are misaligned with matched region of proposals and score of localization, causing a notable gap in performance. In this paper, we propose CPM R-CNN which contains three efficient modules to optimize anchor-based point-guided method. According to sufficient evaluations on the COCO dataset, CPM R-CNN is demonstrated efficient to improve the localization accuracy by calibrating mentioned misalignment. Compared with Faster R-CNN and Grid R-CNN based on ResNet-101 with FPN, our approach can substantially improve detection mAP by 3.3% and 1.5% respectively without whistles and bells. Moreover, our best model achieves improvement by a large margin to 49.9% on COCO test-dev. Code and models will be publicly available.

📄 PDF Abstract BibTeX arXiv:2003.03570

Code (1)

zhubinQAQ/CPM-R-CNN 공식 구현 pytorch

Tasks

object-detection Object Detection

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

FPN 설명 없음

Dilated Convolution 설명 없음

Sigmoid Activation 설명 없음

RoIAlign Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh…

FCN Fully Convolutional Networks, or FCNs, are an architecture used mainly for semantic segmentation. They employ solely locally connected layers, such as…

Grid R-CNN Grid R-CNN is an object detection framework, where the traditional regression formulation is replaced by a grid point guided localization mechanism. Grid R-CNN divides the…

Translation, Scale and Rotation: Cross-Modal Alignment Meets RGB-Infrared Vehicle Detection

2022-09-28 · Maoxun Yuan, Yinyan Wang, Xingxing Wei

Integrating multispectral data in object detection, especially visible and infrared images, has received great attention in recent years. Since visible (RGB) and infrared (IR) images can provide complementary information…

2D Object Detection cross-modal alignment Crowd Counting Multispectral Object Detection+8

Weakly Misalignment-free Adaptive Feature Alignment for UAVs-based Multimodal Object Detection

2024-01-01 · CVPR 2024 1 · Chen Chen, Jiahao Qi, Xingyue Liu, Kangcheng Bin 외

Visible-infrared (RGB-IR) image fusion has shown great potentials in object detection based on unmanned aerial vehicles (UAVs). However the weakly misalignment problem between multimodal image pairs limits its perfor…

2D Object Detection Object object-detection Object Detection

Cal-DETR: Calibrated Detection Transformer

2023-11-06 · NeurIPS 2023 11 · Muhammad Akhtar Munir, Salman Khan, Muhammad Haris Khan, Mohsen Ali 외

Albeit revealing impressive predictive performance for several computer vision tasks, deep neural networks (DNNs) are prone to making overconfident predictions. This limits the adoption and wider utilization of DNNs in m…

Decision Making

COMO: Cross-Mamba Interaction and Offset-Guided Fusion for Multimodal Object Detection

2024-12-24 · Chang Liu, Xin Ma, Xiaochen Yang, Yuxiang Zhang 외

Single-modal object detection tasks often experience performance degradation when encountering diverse scenarios. In contrast, multimodal object detection tasks can offer more comprehensive information about object featu…

Mamba Object object-detection Object Detection

Toward Minimal Misalignment at Minimal Cost in One-Stage and Anchor-Free Object Detection

2021-12-16 · Shuaizheng Hao, Hongzhe Liu, Ningwei Wang, Cheng Xu

Common object detection models consist of classification and regression branches, due to different task drivers, these two branches have different sensibility to the features from the same scale level and the same spatia…

object-detection Object Detection regression