# Revisiting the Sibling Head in Object Detector

arXiv: https://arxiv.org/abs/2003.07540 · HTML: https://mlsanity.com/paper/2003.07540/

## Key facts

- Cited by 82 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Mar 2020.

## Built on by (most cited first, 30 of 82)

- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Learning Spatio-Temporal Transformer for Visual Tracking](https://mlsanity.com/paper/2103.17154/) (2021)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [TOOD: Task-aligned One-stage Object Detection](https://mlsanity.com/paper/2108.07755/) (2021)
- [A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS](https://mlsanity.com/paper/2304.00501/) (2023)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detection](https://mlsanity.com/paper/2209.01814/) (2022)
- [Anchor-Free Person Search](https://mlsanity.com/paper/2103.11617/) (2021)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [Real-time Object Detection for Streaming Perception](https://mlsanity.com/paper/2203.12338/) (2022)
- [CFC-Net: A Critical Feature Capturing Network for Arbitrary-Oriented Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2101.06849/) (2021)
- [ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer](https://mlsanity.com/paper/2308.10147/) (2023)
- [Distilling Self-Supervised Vision Transformers for Weakly-Supervised Few-Shot Classification & Segmentation](https://mlsanity.com/paper/2307.03407/) (2023)
- [Object Detection with Transformers: A Review](https://mlsanity.com/paper/2306.04670/) (2023)
- [DetMatch: Two Teachers are Better Than One for Joint 2D and 3D Semi-Supervised Object Detection](https://mlsanity.com/paper/2203.09510/) (2022)
- [Localization Distillation for Object Detection](https://mlsanity.com/paper/2204.05957/) (2022)
- [Alpha-IoU: A Family of Power Intersection over Union Losses for Bounding Box Regression](https://mlsanity.com/paper/2110.13675/) (2021)
- [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)
- [VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection](https://mlsanity.com/paper/2506.04623/) (2025)
- [VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2103.03768/) (2021)
- [American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers](https://mlsanity.com/paper/2308.12477/) (2023)
- [USB: Universal-Scale Object Detection Benchmark](https://mlsanity.com/paper/2103.14027/) (2021)
- [Mutual Supervision for Dense Object Detection](https://mlsanity.com/paper/2109.05986/) (2021)
- [Efficient OCR for Building a Diverse Digital History](https://mlsanity.com/paper/2304.02737/) (2023)
- [FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network](https://mlsanity.com/paper/2108.04644/) (2021)
- [UniHead: Unifying Multi-Perception for Detection Heads](https://mlsanity.com/paper/2309.13242/) (2023)
- [OGMN: Occlusion-guided Multi-task Network for Object Detection in UAV Images](https://mlsanity.com/paper/2304.11805/) (2023)

## Abstract (arXiv)

The ``shared head for classification and localization'' (sibling head), firstly denominated in Fast RCNN~citegirshick2015fast, has been leading the fashion of the object detection community in the past five years. This paper provides the observation that the spatial misalignment between the two object functions in the sibling head can considerably hurt the training process, but this misalignment can be resolved by a very simple operator called task-aware spatial disentanglement (TSD). Considering the classification and regression, TSD decouples them from the spatial dimension by generating two disentangled proposals for them, which are estimated by the shared proposal. This is inspired by the natural insight that for one instance, the features in some salient area may have rich information for classification while these around the boundary may be good at bounding box regression. Surprisingly, this simple design can boost all backbones and models on both MS COCO and Google OpenImage consistently by ~3% mAP. Further, we propose a progressive constraint to enlarge the performance margin between the disentangled and the shared proposals, and gain ~1% more mAP. We show the algname breaks through the upper bound of nowadays single-model detector by a large margin (mAP 49.4 with ResNet-101, 51.2 with SENet154), and is the core model of our 1st place solution on the Google OpenImage Challenge 2019.