Attention-Guided-Contextual-Feature-Fusion-Network-for-Salient-Object-Detection

This repo. is an implementation of ACFFNet, which is accepted for in Image and Vision Computing.

ACFFNet 实现的github仓库，论文被Image and Vision Computing接收。

This is Pytorch and PaddlePaddle implementation for my paper "Attention Guided Contextual Feature Fusion Network for Salient Object Detection"

Pytorch和飞桨实现的我的论文：注意引导的上下文特征融合网络用于显著目标检测

The paper will be provided after publication

论文发表后将会提供

The PaddlePaddle codes are being prepared for upload

飞桨版本的代码正在准备上传中

We have prepared the saliency maps on five datasets

我们已经准备了5个数据集的显著图

you can find the saliency maps on DUTS-TE、ECSSD、HKU-IS、DUT-OMRON and PASCAL-S datasets and the weight pth file from Google Driver link here and the Baidu online disk link (The extraction code is: ACFF) here

DUTS-TE、ECSSD、HKU-IS、DUT-OMRON和PASCAL-S数据集上预测的显著图和模型的权重可以从Google Driver链接这里 和百度网盘链接(提取码为：ACFF) 这里找到

We use the code provided by this repo. to calculate the metrics

我们使用这个仓库提供的代码来计算指标

The effect of ACFFNet on 5 benchmark datasets is as follows：

ACFFNet在5个基准数据集上的效果如下