# R-FCN-3000 at 30fps: Decoupling Detection and Classification

arXiv: https://arxiv.org/abs/1712.01802 · HTML: https://mlsanity.com/paper/1712.01802/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Dec 2017.

## Built on by (most cited first, 15 of 15)

- [RegionCLIP: Region-based Language-Image Pretraining](https://mlsanity.com/paper/2112.09106/) (2021)
- [Detecting Twenty-thousand Classes using Image-level Supervision](https://mlsanity.com/paper/2201.02605/) (2022)
- [Cross-Domain Adaptive Teacher for Object Detection](https://mlsanity.com/paper/2111.13216/) (2021)
- [Learning Open-World Object Proposals without Learning to Classify](https://mlsanity.com/paper/2108.06753/) (2021)
- [GROUNDHOG: Grounding Large Language Models to Holistic Segmentation](https://mlsanity.com/paper/2402.16846/) (2024)
- [Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding](https://mlsanity.com/paper/2206.03484/) (2022)
- [Taming Self-Training for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2308.06412/) (2023)
- [World-to-Words: Grounded Open Vocabulary Acquisition through Fast Mapping in Vision-Language Models](https://mlsanity.com/paper/2306.08685/) (2023)
- [Open-Vocabulary Object Detection via Language Hierarchy](https://mlsanity.com/paper/2410.20371/) (2024)
- [3D Cascade RCNN: High Quality Object Detection in Point Clouds](https://mlsanity.com/paper/2211.08248/) (2022)
- [V-MIND: Building Versatile Monocular Indoor 3D Detector with Diverse 2D Annotations](https://mlsanity.com/paper/2412.11412/) (2024)
- [EcoSense: Energy-Efficient Intelligent Sensing for In-Shore Ship Detection through Edge-Cloud Collaboration](https://mlsanity.com/paper/2403.14027/) (2024)
- [VK-Det: Visual Knowledge Guided Prototype Learning for Open-Vocabulary Aerial Object Detection](https://mlsanity.com/paper/2511.18075/) (2025)
- [Weak Novel Categories without Tears: A Survey on Weak-Shot Learning](https://mlsanity.com/paper/2110.02651/) (2021)
- [Towards Establishing Systematic Classification Requirements for Automated Driving](https://mlsanity.com/paper/2307.14058/) (2023)

## Abstract (arXiv)

We present R-FCN-3000, a large-scale real-time object detector in which objectness detection and classification are decoupled. To obtain the detection score for an RoI, we multiply the objectness score with the fine-grained classification score. Our approach is a modification of the R-FCN architecture in which position-sensitive filters are shared across different object classes for performing localization. For fine-grained classification, these position-sensitive filters are not needed. R-FCN-3000 obtains an mAP of 34.9% on the ImageNet detection dataset and outperforms YOLO-9000 by 18% while processing 30 images per second. We also show that the objectness learned by R-FCN-3000 generalizes to novel classes and the performance increases with the number of training object classes - supporting the hypothesis that it is possible to learn a universal objectness detector. Code will be made available.