Scene recognition is one of the hallmark tasks of computer vision, allowing defining a context for object recognition. Using convolutional neural network (CNN), we learn deep scene features for scene recognition tasks.

Scene recognition is one of the hallmark tasks of computer vision, allowing defining a context for object recognition. Here we introduce a new scene-centric database with 365 scene categories and 2.5 millions of images with a category label where there are at most 5000 images per category. Using convolutional neural network (CNN), we learn deep scene features for scene recognition tasks .

Download the models from here

Please cite the following IEEE Transaction on Pattern Analysis and Machine Intelligence paper if you use the data or pre-trained CNN models.

 @article{zhou2017places,
   title={Places: A 10 million Image Database for Scene Recognition},
   author={Zhou, Bolei and Lapedriza, Agata and Khosla, Aditya and Oliva, Aude and Torralba, Antonio},
   journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
   year={2017},
   publisher={IEEE}
 }

The pretrained places-CNN models can be used under the Creative Common License (Attribution CC BY). The copyright of all the images belongs to the image owners.