paper-with-me

Papers

MSFM: Multi-Scale Fusion Module for Object Detection

2021-01-01 · Xuesong Wang, Caisheng Wang

Feature fusion is beneficial to object detection tasks in two folds. On one hand, detail and position information can be combined with semantic information when high and low-resolution features from shallow and deep layers are fused. On the other hand, objects can be detected in different scales, which improves the robustness of the framework. In this work, we present a Multi-Scale Fusion Module (MSFM) that extracts both detail and semantical information from a single input but at different scales within the same layer. Specifically, the input of the module will be resized into different scales on which position and semantic information will be processed, and then they will be rescaled back and combined with the module input. The MSFM is lightweight and can be used as a drop-in layer to many existing object detection frameworks. Experiments show that MSFM can bring +2.5% mAP improvement with only 2.4M extra parameters on Faster R-CNN with ResNet-50 FPN backbone on COCO Object Detection minival set, outperforming that with ResNet-101 FPN backbone without the module which obtains +2.0% mAP with 19.0M extra parameters. The best resulting model achieves a 45.7% mAP on test-dev set. Code will be available.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detectionObject DetectionPosition

Methods 이 논문이 사용한 방법론

RoIPool 설명 없음
RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…
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 $x$…
Faster R-CNN Faster R-CNN is an object detection model that improves on Fast R-CNN by utilising a region proposal network…
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…
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

Similar Papers 제목 키워드 기반

TSNet:A Two-stage Network for Image Dehazing with Multi-scale Fusion and Adaptive Learning

2024-04-03 · Xiaolin Gong, Zehan Zheng, Heyuan Du

Image dehazing has been a popular topic of research for a long time. Previous deep learning-based image dehazing methods have failed to achieve satisfactory dehazing effects on both synthetic datasets and real-world data…

Image Dehazing

R-MSFM: Recurrent Multi-Scale Feature Modulation for Monocular Depth Estimating

2021-01-01 · ICCV 2021 10 · Zhongkai Zhou, Xinnan Fan, Pengfei Shi, Yuanxue Xin

In this paper, we propose Recurrent Multi-Scale Feature Modulation (R-MSFM), a new deep network architecture for self-supervised monocular depth estimation. R-MSFM extracts per-pixel features, builds a multi-scale fe…

DecoderDepth EstimationMonocular Depth Estimation

MSFMamba: Multi-Scale Feature Fusion State Space Model for Multi-Source Remote Sensing Image Classification

2024-08-26 · Feng Gao, Xuepeng Jin, Xiaowei Zhou, Junyu Dong 외

In the field of multi-source remote sensing image classification, remarkable progress has been made by using Convolutional Neural Network (CNN) and Transformer. Recently, Mamba-based methods built upon the State Space Mo…

Computational Efficiencyimage-classificationImage ClassificationMamba+1

Two Methods for Spoofing-Aware Speaker Verification: Multi-Layer Perceptron Score Fusion Model and Integrated Embedding Projector

2022-06-28 · Jungwoo Heo, Ju-ho Kim, Hyun-seo Shin

The use of deep neural networks (DNN) has dramatically elevated the performance of automatic speaker verification (ASV) over the last decade. However, ASV systems can be easily neutralized by spoofing attacks. Therefore,…

Speaker Verification

MATCNN: Infrared and Visible Image Fusion Method Based on Multi-scale CNN with Attention Transformer

2025-02-04 · Jingjing Liu, Li Zhang, Xiaoyang Zeng, Wanquan Liu 외

While attention-based approaches have shown considerable progress in enhancing image fusion and addressing the challenges posed by long-range feature dependencies, their efficacy in capturing local features is compromise…

Infrared And Visible Image Fusion