Paper ID | IVMSP-4.4 | ||
Paper Title | IMAGE CODING FOR MACHINES: AN END-TO-END LEARNED APPROACH | ||
Authors | Nam Le, Tampere University, Finland; Honglei Zhang, Francesco Cricri, Ramin Ghaznavi Youvalari, Nokia Technologies, Finland; Esa Rahtu, Tampere University, Finland | ||
Session | IVMSP-4: Image & Video Coding 2 | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 14:00 - 14:45 | ||
Presentation Time: | Tuesday, 08 June, 14:00 - 14:45 | ||
Presentation | Poster | ||
Topic | Image, Video, and Multidimensional Signal Processing: [IVCOM] Image & Video Communications | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Over recent years, deep learning-based computer vision systems have been applied to images at an ever-increasing pace, oftentimes representing the only type of consumption for those images. Given the dramatic explosion in the number of images generated per day, a question arises: how much better would an image codec targeting machine-consumption perform against state-of-the-art codecs targeting human-consumption? In this paper, we propose an image codec for machines which is neural network (NN) based and end-to-end learned. In particular, we propose a set of training strategies that address the delicate problem of balancing competing loss functions, such as computer vision task losses, image distortion losses, and rate loss. Our experimental results show that our NN-based codec outperforms the state-of-the-art Versatile Video Coding (VVC) standard on the object detection and instance segmentation tasks, achieving -37.87% and -32.90% of BD-rate gain, respectively, while being fast thanks to its compact size. To the best of our knowledge, this is the first end-to-end learned machine-targeted image codec. |