# Subcategory-aware Convolutional Neural Networks for Object Proposals and Detection

arXiv: https://arxiv.org/abs/1604.04693 · HTML: https://mlsanity.com/paper/1604.04693/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Apr 2016.

## Built on by (most cited first, 17 of 17)

- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Monocular 3D Object Detection: An Extrinsic Parameter Free Approach](https://mlsanity.com/paper/2106.15796/) (2021)
- [GrooMeD-NMS: Grouped Mathematically Differentiable NMS for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.17202/) (2021)
- [WEDGE: A multi-weather autonomous driving dataset built from generative vision-language models](https://mlsanity.com/paper/2305.07528/) (2023)
- [Domain-Specific Suppression for Adaptive Object Detection](https://mlsanity.com/paper/2105.03570/) (2021)
- [TrackMPNN: A Message Passing Graph Neural Architecture for Multi-Object Tracking](https://mlsanity.com/paper/2101.04206/) (2021)
- [PLUMENet: Efficient 3D Object Detection from Stereo Images](https://mlsanity.com/paper/2101.06594/) (2021)
- [MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer](https://mlsanity.com/paper/2303.13018/) (2023)
- [A step towards understanding why classification helps regression](https://mlsanity.com/paper/2308.10603/) (2023)
- [MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation](https://mlsanity.com/paper/2303.13561/) (2023)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [HoughNet: Integrating near and long-range evidence for visual detection](https://mlsanity.com/paper/2104.06773/) (2021)
- [Pose Estimation and 3D Reconstruction of Vehicles from Stereo-Images Using a Subcategory-Aware Shape Prior](https://mlsanity.com/paper/2107.10898/) (2021)
- [Enhanced Cooperative Perception for Autonomous Vehicles Using Imperfect Communication](https://mlsanity.com/paper/2404.08013/) (2024)
- [TEC: Tensor Ensemble Classifier for Big Data](https://mlsanity.com/paper/2103.00025/) (2021)
- [Self-supervised Learning of 3D Object Understanding by Data Association and Landmark Estimation for Image Sequence](https://mlsanity.com/paper/2104.07077/) (2021)
- [Context-aware 6D Pose Estimation of Known Objects using RGB-D data](https://mlsanity.com/paper/2212.05560/) (2022)

## Abstract (arXiv)

In CNN-based object detection methods, region proposal becomes a bottleneck when objects exhibit significant scale variation, occlusion or truncation. In addition, these methods mainly focus on 2D object detection and cannot estimate detailed properties of objects. In this paper, we propose subcategory-aware CNNs for object detection. We introduce a novel region proposal network that uses subcategory information to guide the proposal generating process, and a new detection network for joint detection and subcategory classification. By using subcategories related to object pose, we achieve state-of-the-art performance on both detection and pose estimation on commonly used benchmarks.