https://github.com/shivam-21-11/basnet-model_package
BASNet: Boundary-Aware Salient Object Detection
https://github.com/shivam-21-11/basnet-model_package
computer-vision image-segmentation obejct-detection tensorflow
Last synced: 20 days ago
JSON representation
BASNet: Boundary-Aware Salient Object Detection
- Host: GitHub
- URL: https://github.com/shivam-21-11/basnet-model_package
- Owner: Shivam-21-11
- License: mit
- Created: 2022-09-03T04:25:35.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2022-09-03T06:33:49.000Z (almost 4 years ago)
- Last Synced: 2025-09-21T08:57:03.970Z (10 months ago)
- Topics: computer-vision, image-segmentation, obejct-detection, tensorflow
- Language: Python
- Homepage:
- Size: 27.3 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# SOD-BASNET-Py
*This is Official repository for the SODBASNET python module*
# BASNet: Boundary-Aware Salient Object Detection
- Deep Convolutional Neural Networks have been adopted for salient object detection and achieved the state-of-the-art performance. Most of the previous works however focus on region accuracy but not on the boundary quality.
- In this project, we propose a predict-refine architecture, BASNet, and a new hybrid loss for Boundary-Aware Salient object detection. Specifically, the architecture is composed of a densely supervised Encoder-Decoder network and a residual refinement module, which are respectively in charge of saliency prediction and saliency map refinement.
- The Research paper referred is [BASNet: Boundary-Aware Salient Object Detection](https://openaccess.thecvf.com/content_CVPR_2019/papers/Qin_BASNet_Boundary-Aware_Salient_Object_Detection_CVPR_2019_paper.pdf "BASNet: Boundary-Aware Salient Object Detection")
## Objective
- The Official Code for the Basnet Model is provided by the authors on the [github](https://github.com/xuebinqin/BASNet "github").
- The Official Deep Learning model is made using Pytorch , my Goal is to create a similar model using tensorflow.
- Why ? Whilst Pytorch provide better developer experience and error handeling, I find Tensorflow to be a great ML Framework to work with for Beginners .
- So the objective for this repo is to create Basnet Model using Tensorflow.
## Architecture
- The Architecture Proposed by the authors is predict-refine architecture.
- The Author have used Transfer Learning to improve model performance . They Used First 4 layers of the resnet34 model which is pretrained in imagenet dataset.
- But for the sake of understanding abstract architecture of the Basnet model I haven't used the transfer learning method , instead created each layer individually.
## Loss
- The hybrid loss guides the network to learn the transformation between the input image and the ground truth in a three-level hierarchy – pixel-, patch- and map- level – by fusing Binary Cross Entropy (BCE), Structural SIMilarity (SSIM) and Intersectionover- Union (IoU) losses.
# Usage Example
Pip installing SODBASNET
`pip install SODBASNET`
Importing Basnet Model
```python
from BASNET import BasNet
from BASNET import iou_loss,ssim_loss,binary_crossentropy
model = BasNet()
model.compile(optimizer='adam',
loss=[iou_loss,ssim_loss,binary_crossentropy],
metrics = ['accuracy'])
```
## Thank You
- This is my attempt to build the Basnet model using the research paper . If you find any error or mistakes let me know . Love all the feedbacks.