2021/12/17 by Guang‐Yu Guo, Dingwen Zhang, Guo, Guangyu +7 · 1 citation
Computer Science · Engineering · Mathematics · #Advanced Image Processing Techniques #Advanced Neural Network Applications #Artificial intelligence #Artificial neural network #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Data mining #Deep learning #Distillation #FOS: Computer and information sciences #Feature (linguistics) #Image (mathematics) #Image Processing Techniques and Applications #Inference #Machine Learning (cs.LG) #Machine learning #Mathematics #Pascal (unit) #Pattern recognition (psychology) #Pixel #Resolution (logic) #Scheme (mathematics)
paper · pdf · doi:10.48550/arxiv.2112.09532
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2021/12/17 · openalex created_date 2022/05/05 · openalex updated_date 2026/07/28
Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size. Therefore, we propose Pixel Distillation that extends knowledge distillation into the input level while simultaneously breaking architecture constraints. Such a scheme can achieve flexible cost control for deployment, as it allows the system to adjust both network architecture and image quality according to the overall requirement of resources. Specifically, we first propose an input spatial representation distillation (ISRD) mechanism to transfer spatial knowledge from large images to student's input module, which can facilitate stable knowledge transfer between CNN and ViT. Then, a Teacher-Assistant-Student (TAS) framework is further established to disentangle pixel distillation into the model compression stage and input compression stage, which significantly reduces the overall complexity of pixel distillation and the difficulty of distilling intermediate knowledge. Finally, we adapt pixel distillation to object detection via an aligned feature for preservation (AFP) strategy for TAS, which aligns output dimensions of detectors at each stage by manipulating features and anchors of the assistant. Comprehensive experiments on image classification and object detection demonstrate the effectiveness of our method. Code is available at https://github.com/gyguo/PixelDistillation.