# DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution

arXiv: https://arxiv.org/abs/2006.02334 · HTML: https://mlsanity.com/paper/2006.02334/

## Key facts

- Cited by 222 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2020.

## Built on by (most cited first, 30 of 222)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP](https://mlsanity.com/paper/2308.02487/) (2023)
- [Towards Open Vocabulary Learning: A Survey](https://mlsanity.com/paper/2306.15880/) (2023)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions](https://mlsanity.com/paper/2206.08171/) (2022)
- [A Survey of Modern Deep Learning based Object Detection Models](https://mlsanity.com/paper/2104.11892/) (2021)
- [RigNet: Repetitive Image Guided Network for Depth Completion](https://mlsanity.com/paper/2107.13802/) (2021)
- [Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation](https://mlsanity.com/paper/2204.04656/) (2022)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [OMG-Seg: Is One Model Good Enough For All Segmentation?](https://mlsanity.com/paper/2401.10229/) (2024)
- [Mitosis domain generalization in histopathology images -- The MIDOG challenge](https://mlsanity.com/paper/2204.03742/) (2022)
- [Lite Vision Transformer with Enhanced Self-Attention](https://mlsanity.com/paper/2112.10809/) (2021)
- [CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation](https://mlsanity.com/paper/2206.08948/) (2022)
- [Part-aware Panoptic Segmentation](https://mlsanity.com/paper/2106.06351/) (2021)
- [Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark](https://mlsanity.com/paper/2206.13996/) (2022)
- [A Large-scale Multiple-objective Method for Black-box Attack against Object Detection](https://mlsanity.com/paper/2209.07790/) (2022)
- [A Normalized Gaussian Wasserstein Distance for Tiny Object Detection](https://mlsanity.com/paper/2110.13389/) (2021)
- [RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection](https://mlsanity.com/paper/2208.08738/) (2022)
- [GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021](https://mlsanity.com/paper/2202.11983/) (2022)
- [Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection](https://mlsanity.com/paper/2304.08876/) (2023)
- [The SARAS Endoscopic Surgeon Action Detection (ESAD) dataset: Challenges and methods](https://mlsanity.com/paper/2104.03178/) (2021)
- [Panoptic-PartFormer: Learning a Unified Model for Panoptic Part Segmentation](https://mlsanity.com/paper/2204.04655/) (2022)
- [DISCO: accurate Discrete Scale Convolutions](https://mlsanity.com/paper/2106.02733/) (2021)
- [PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation](https://mlsanity.com/paper/2112.02582/) (2021)
- [Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR](https://mlsanity.com/paper/2303.07335/) (2023)
- [TubeFormer-DeepLab: Video Mask Transformer](https://mlsanity.com/paper/2205.15361/) (2022)

## Abstract (arXiv)

Many modern object detectors demonstrate outstanding performances by using the mechanism of looking and thinking twice. In this paper, we explore this mechanism in the backbone design for object detection. At the macro level, we propose Recursive Feature Pyramid, which incorporates extra feedback connections from Feature Pyramid Networks into the bottom-up backbone layers. At the micro level, we propose Switchable Atrous Convolution, which convolves the features with different atrous rates and gathers the results using switch functions. Combining them results in DetectoRS, which significantly improves the performances of object detection. On COCO test-dev, DetectoRS achieves state-of-the-art 55.7% box AP for object detection, 48.5% mask AP for instance segmentation, and 50.0% PQ for panoptic segmentation. The code is made publicly available.