# DetNet: A Backbone network for Object Detection Source: [DetNet: A Backbone network for Object Detection]() Collection index: [llms.txt]() Data updated: 2025-10-25T20:59:11.405Z Authors: Zeming Li, Chao Peng, Gang Yu, Xiangyu Zhang, Yangdong Deng, Jian Sun Published: 2018-04-17T13:09:13.000Z ## Abstract Recent CNN based object detectors, no matter one-stage methods like YOLO, SSD, and RetinaNe or two-stage detectors like Faster R-CNN, R-FCN and FPN are usually trying to directly finetune from ImageNet pre-trained models designed for image classification. There has been little work discussing on the backbone feature extractor specifically designed for the object detection. More importantly, there are several differences between the tasks of image classification and object detection. 1. Recent object detectors like FPN and RetinaNet usually involve extra stages against the task of image classification to handle the objects with various scales. 2. Object detection not only needs to recognize the category of the object instances but also spatially locate the position. Large downsampling factor brings large valid receptive field, which is good for image classification but compromises the object location ability. Due to the gap between the image classification and object detection, we propose DetNet in this paper, which is a novel backbone network specifically designed for object detection. Moreover, DetNet includes the extra stages against traditional backbone network for image classification, while maintains high spatial resolution in deeper layers. Without any bells and whistles, state-of-the-art results have been obtained for both object detection and instance segmentation on the MSCOCO benchmark based on our DetNet~(4.8G FLOPs) backbone. The code will be released for the reproduction. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Object Detection on COCO (minival)](): Object Detection; COCO (minival); mAP: 34.5. - [Video Classification on Kinetics 400 (val)](): Video Classification; Kinetics 400 (val); Top-1 Acc: 73.3. ## Original sources and implementation [Original paper]() [PDF]()