2020/04/25 by Dongzhan Zhou, Xinchi Zhou, Zhou, Dongzhan +7 · 1 citation
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #cs.CV
paper · pdf · doi:10.48550/arxiv.2004.12178
Accepted by ECCV2020
openalex publication_date 2020/04/25 · arxiv created 2020/08/31 · arxiv updated 2020/09/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In this paper, we propose a general and efficient pre-training paradigm, Montage pre-training, for object detection. Montage pre-training needs only the target detection dataset while taking only 1/4 computational resources compared to the widely adopted ImageNet pre-training.To build such an efficient paradigm, we reduce the potential redundancy by carefully extracting useful samples from the original images, assembling samples in a Montage manner as input, and using an ERF-adaptive dense classification strategy for model pre-training. These designs include not only a new input pattern to improve the spatial utilization but also a novel learning objective to expand the effective receptive field of the pretrained model. The efficiency and effectiveness of Montage pre-training are validated by extensive experiments on the MS-COCO dataset, where the results indicate that the models using Montage pre-training are able to achieve on-par or even better detection performances compared with the ImageNet pre-training.