# DetNet: A Backbone network for Object Detection

arXiv: https://arxiv.org/abs/1804.06215 · HTML: https://mlsanity.com/paper/1804.06215/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2018.

## Built on by (most cited first, 22 of 22)

- [TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios](https://mlsanity.com/paper/2108.11539/) (2021)
- [TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search](https://mlsanity.com/paper/2105.11871/) (2021)
- [Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations](https://mlsanity.com/paper/2104.10824/) (2021)
- [Deep Learning for UAV-based Object Detection and Tracking: A Survey](https://mlsanity.com/paper/2110.12638/) (2021)
- [Dropout Reduces Underfitting](https://mlsanity.com/paper/2303.01500/) (2023)
- [Boosting vision transformers for image retrieval](https://mlsanity.com/paper/2210.11909/) (2022)
- [Backbones-Review: Feature Extraction Networks for Deep Learning and Deep Reinforcement Learning Approaches](https://mlsanity.com/paper/2206.08016/) (2022)
- [YOLO-FaceV2: A Scale and Occlusion Aware Face Detector](https://mlsanity.com/paper/2208.02019/) (2022)
- [A Guide to Image and Video based Small Object Detection using Deep Learning : Case Study of Maritime Surveillance](https://mlsanity.com/paper/2207.12926/) (2022)
- [YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs](https://mlsanity.com/paper/2110.13713/) (2021)
- [Precise Single-stage Detector](https://mlsanity.com/paper/2210.04252/) (2022)
- [NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models](https://mlsanity.com/paper/2108.03434/) (2021)
- [A Systematic IoU-Related Method: Beyond Simplified Regression for Better Localization](https://mlsanity.com/paper/2112.01793/) (2021)
- [LEDetection: A Simple Framework for Semi-Supervised Few-Shot Object Detection](https://mlsanity.com/paper/2303.05739/) (2023)
- [Precise Apple Detection and Localization in Orchards using YOLOv5 for Robotic Harvesting Systems](https://mlsanity.com/paper/2405.06260/) (2024)
- [Colonoscopy polyp detection with massive endoscopic images](https://mlsanity.com/paper/2202.08730/) (2022)
- [CASSOD-Net: Cascaded and Separable Structures of Dilated Convolution for Embedded Vision Systems and Applications](https://mlsanity.com/paper/2104.14126/) (2021)
- [A Study on Representation Transfer for Few-Shot Learning](https://mlsanity.com/paper/2209.02073/) (2022)
- [Stall Number Detection of Cow Teats Key Frames](https://mlsanity.com/paper/2303.10444/) (2023)
- [A novel Multi to Single Module for small object detection](https://mlsanity.com/paper/2303.14977/) (2023)
- [Hebrew letters Detection and Cuneiform tablets Classification by using the yolov8 computer vision model](https://mlsanity.com/paper/2407.06133/) (2024)
- [Accelerating Object Detection with YOLOv4 for Real-Time Applications](https://mlsanity.com/paper/2410.16320/) (2024)

## Abstract (arXiv)

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.