Semantic-Aware Scene Recognition

Official Pytorch Implementation of Semantic-Aware Scene Recognition by Alejandro López-Cifuentes, Marcos Escudero-Viñolo, Jesús Bescós and Álvaro García-Martín (Elsevier Pattern Recognition).

Summary

This paper propose to improve scene recognition by using object information to focalize learning during the training process. The main contributions of the paper are threefold:

• We propose an end-to-end multi-modal deep learning architecture which gathers both image and context information using a two-branched CNN architecture.
• We propose to use semantic segmentation as an additional information source to automatically create, through a convolutional neural network, an attention model to reinforce the learning of relevant contextual information.
• We validate the effectiveness of the proposed method through experimental results on public scene recognition datasets such as ADE20K, MIT Indoor 67, SUN 397 and Places365 obtaining state-of-the-art results.

The propose CNN architecture is as follows:

State-of-the-art Results

ADE20K Dataset

MIT Indoor 67 Dataset

SUN 397 Dataset

Places 365 Dataset

Setup

Requirements

The repository has been tested in the following software versions.

• Ubuntu 16.04
• Python 3.6
• Anaconda 4.6

Clone Repository

Clone repository running the following command:

$ git clone https://github.com/vpulab/Semantic-Aware-Scene-Recognition.git

Anaconda Enviroment

To create and setup the Anaconda Envirmorent run the following terminal command from the repository folder:

$ conda env create -f Config/Conda_Env.yml
$ conda activate SA-Scene-Recognition

Datasets

Download and setup instructions for each datasets are provided in the follwing links:

• ADE20K
• MIT Indoor 67
• SUN 397
• Places 365

Evaluation

Model Zoo

In order to evaluate the models independently, download them from the following links and indicate the path in YAML configuration files (Usually /Data/Model Zoo/DATASET FOLDER).

[Recommended] Alternatively you can run the following script from the repository folder to download all the available Model Zoo:

bash ./Scripts/download_ModelZoo.sh

ADE20K

• Ours
• RGB Branch
• Semantic Branch

MIT Indoor 67

• Ours (ResNet-18 backbone)
• Ours* (ResNet-50 backbone)
• RGB Branch (ResNet-18 backbone)
• RGB Branch* (ResNet-50 backbone)
• Semantic Branch

SUN 397

• Ours (ResNet-18 backbone)
• Ours* (ResNet-50 backbone)
• RGB Branch (ResNet-18 backbone)
• RGB Branch* (ResNet-50 backbone)
• Semantic Branch

Places 365

• Ours
• RGB Branch
• Semantic Branch

Run Evaluation

In order to evaluate models run evaluation.py file from the respository folder indicating the dataset YAML configuration path:

python evaluation.py --ConfigPath [PATH to configuration file]

Example for ADE20K Dataset:

python evaluation.py --ConfigPath Config/config_ADE20K.yaml

All the desired configuration (backbone architecture to use, model to load, batch size...etc) should be changed in each separate YAML configuration file.

Computed performance metrics for both training and validation sets are:

• Top@1
• Top@2
• Top@5
• Mean Class Accuracy (MCA)

Citation

If you find this code and work useful, please consider citing:

@article{lopez2020semantic,
  title={Semantic-Aware Scene Recognition},
  author={L{\'o}pez-Cifuentes, Alejandro and Escudero-Vi{\~n}olo, Marcos and Besc{\'o}s, Jes{\'u}s and Garc{\'\i}a-Mart{\'\i}n, {\'A}lvaro},
  journal={Pattern Recognition},
  pages={107256},
  year={2020},
  publisher={Elsevier}
}

Acknowledgment

This study has been partially supported by the Spanish Government through its TEC2017-88169-R MobiNetVideo project.