upload init codes

.gitignore

@@ -30,3 +30,4 @@
 *.exe
 *.out
 *.app
+/snapshot/20201214-Network_Res2Net_GRA_NCD/

README.md

@@ -1,2 +1,131 @@
-# SINet-V2
-Search and Identification Network Version-2
+# Concealed Object Detection (TPAMI-2021)
+
+> **Authors:** 
+> [Deng-Ping Fan](https://dpfan.net/), 
+> [Ge-Peng Ji](https://scholar.google.com/citations?user=oaxKYKUAAAAJ&hl=en), 
+> [Ming-Ming Cheng](https://mmcheng.net/),
+> [Ling Shao](http://www.inceptioniai.org/).
+
+## 1. Preface
+
+- **Introduction.** This repository contains the source code, prediction results, and evaluation toolbox of our method, which is the 
+journal extension version of our paper SINet (github) published at CVPR-2020.
+
+- **Highlights.** Compared to our conference version, we achieve new SOTA in the field of COD via the two 
+well-elaborated sub-modules, including neighbor connection decoder(NCD) and group-reversal attention (GRA). 
+Please refer to our paper for more details.
+
+> If you have any questions about our paper, feel free to contact me via e-mail ([email protected]). 
+> And if you are using our our and evaluation toolbox for your research, please cite this paper ([BibTeX](#4-citation)).
+
+
+## 2. :fire: NEWS :fire:
+
+- [2021/01/16] Create repository.
+
+
+## 3. Overview
+
+<p align="center">
+    <img src="imgs/TaskRelationship.png"/> <br />
+    <em> 
+    Figure 1: Task relationship. One of the most popular directions in computer vision is generic object detection. 
+    Note that generic objects can be either salient or camouflaged; camouflaged objects can be seen as difficult cases of 
+    generic objects. Typical generic object detection tasks include semantic segmentation and panoptic 
+    segmentation (see Fig. 2 b).
+    </em>
+</p>
+
+<p align="center">
+    <img src="imgs/CamouflagedTask.png"/> <br />
+    <em> 
+    Figure 2: Given an input image (a), we present the ground-truth for (b) panoptic segmentation 
+    (which detects generic objects including stuff and things), (c) salient instance/object detection 
+    (which detects objects that grasp human attention), and (d) the proposed camouflaged object detection task, 
+    where the goal is to detect objects that have a similar pattern (e.g., edge, texture, or color) to the natural habitat. 
+    In this case, the boundaries of the two butterflies are blended with the bananas, making them difficult to identify. 
+    This task is far more challenging than the traditional salient object detection or generic object detection.
+    </em>
+</p>
+
+> References of Salient Object Detection (SOD) benchmark works<br>
+> [1] Video SOD: Shifting More Attention to Video Salient Object Detection. CVPR, 2019. ([Project Page](http://dpfan.net/davsod/))<br>
+> [2] RGB SOD: Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground. ECCV, 2018. ([Project Page](https://dpfan.net/socbenchmark/))<br>
+> [3] RGB-D SOD: Rethinking RGB-D Salient Object Detection: Models, Datasets, and Large-Scale Benchmarks. TNNLS, 2020. ([Project Page](http://dpfan.net/d3netbenchmark/))<br>
+> [4] Co-SOD: Taking a Deeper Look at the Co-salient Object Detection. CVPR, 2020. ([Project Page](http://dpfan.net/CoSOD3K/))
+
+
+## 4. Proposed Framework
+
+### 4.1. Training/Testing
+
+The training and testing experiments are conducted using [PyTorch](https://github.com/pytorch/pytorch) with 
+a single GeForce RTX TITAN GPU of 24 GB Memory.
+
+> Note that our model also supports low memory GPU, which means you should lower the batch size.
+
+1. Prerequisites:
+
+    Note that SINet is only tested on Ubuntu OS with the following environments. 
+    It may work on other operating systems as well but we do not guarantee that it will.
+
+    + Creating a virtual environment in terminal: `conda create -n SINet python=3.6`.
+
+    + Installing necessary packages: [PyTorch > 1.1](https://pytorch.org/), [opencv-python](https://pypi.org/project/opencv-python/)
+
+1. Prepare the data:
+
+    + downloading testing dataset and move it into `./data/TestDataset/`, 
+    which can be found in this [download link (Google Drive)](https://drive.google.com/file/d/1o8OfBvYE6K-EpDyvzsmMPndnUMwb540R/view?usp=sharing).
+
+    + downloading training dataset and move it into `./data/TrainDataset/`, 
+    which can be found in this [download link (Google Drive)](https://drive.google.com/file/d/1lODorfB33jbd-im-qrtUgWnZXxB94F55/view?usp=sharing).
+
+    + downloading pretrained weights and move it into `snapshots/PraNet_Res2Net/PraNet-19.pth`, 
+    which can be found in this [download link (Google Drive)](https://drive.google.com/file/d/1pUE99SUQHTLxS9rabLGe_XTDwfS6wXEw/view?usp=sharing).
+
+    + downloading Res2Net weights [download link (Google Drive)](https://drive.google.com/file/d/1_1N-cx1UpRQo7Ybsjno1PAg4KE1T9e5J/view?usp=sharing).
+
+1. Training Configuration:
+
+    + Assigning your costumed path, like `--train_save` and `--train_path` in `MyTrain_Val.py`.
+
+    + Just enjoy it!
+
+1. Testing Configuration:
+
+    + After you download all the pre-trained model and testing dataset, just run `MyTesting.py` to generate the final prediction map: 
+    replace your trained model directory (`--pth_path`).
+
+    + Just enjoy it!
+
+### 3.2 Evaluating your trained model:
+
+One-key evaluation is written in MATLAB code ([link](https://drive.google.com/file/d/1_h4_CjD5GKEf7B1MRuzye97H0MXf2GE9/view?usp=sharing)), 
+please follow this the instructions in `./eval/main.m` and just run it to generate the evaluation results in `./res/`.
+The complete evaluation toolbox (including data, map, eval code, and res): [link](https://drive.google.com/file/d/1qga1UJlIQdHNlt_F9TdN4lmmOH4gN7l2/view?usp=sharing). 
+
+### 3.3 Pre-computed maps: 
+They can be found in [download link](https://drive.google.com/file/d/1tW0OOxPSuhfSbMijaMPwRDPElW1qQywz/view?usp=sharing).
+
+
+## 4. Citation
+
+Please cite our paper if you find the work useful: 
+
+    @article{fan2020pra,
+    title={PraNet: Parallel Reverse Attention Network for Polyp Segmentation},
+    author={Fan, Deng-Ping and Ji, Ge-Peng and Zhou, Tao and Chen, Geng and Fu, Huazhu and Shen, Jianbing and Shao, Ling},
+    journal={MICCAI},
+    year={2020}
+    }
+
+## 6. FAQ
+
+1. If the image cannot be loaded in the page (mostly in the domestic network situations).
+
+    [Solution Link](https://blog.csdn.net/weixin_42128813/article/details/102915578)
+
+---
+
+**[⬆ back to top](#0-preface)**