# Disentangle Your Dense Object Detector

arXiv: https://arxiv.org/abs/2107.02963 · HTML: https://mlsanity.com/paper/2107.02963/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 57 of its 65 references that are in the map.
- First posted on arXiv 7 Jul 2021.

## Builds on (most cited first, 30 of 57)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [Cascade R-CNN: Delving into High Quality Object Detection](https://mlsanity.com/paper/1712.00726/) (2017)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [CornerNet: Detecting Objects as Paired Keypoints](https://mlsanity.com/paper/1808.01244/) (2018)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection](https://mlsanity.com/paper/1912.02424/) (2019)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection](https://mlsanity.com/paper/2006.04388/) (2020)
- [WIDER FACE: A Face Detection Benchmark](https://mlsanity.com/paper/1511.06523/) (2015)
- [Equalization Loss for Long-Tailed Object Recognition](https://mlsanity.com/paper/2003.05176/) (2020)
- [RepPoints: Point Set Representation for Object Detection](https://mlsanity.com/paper/1904.11490/) (2019)
- [Libra R-CNN: Towards Balanced Learning for Object Detection](https://mlsanity.com/paper/1904.02701/) (2019)
- [Scaled-YOLOv4: Scaling Cross Stage Partial Network](https://mlsanity.com/paper/2011.08036/) (2020)
- [Acquisition of Localization Confidence for Accurate Object Detection](https://mlsanity.com/paper/1807.11590/) (2018)
- [RetinaFace: Single-stage Dense Face Localisation in the Wild](https://mlsanity.com/paper/1905.00641/) (2019)
- [Scale-Aware Trident Networks for Object Detection](https://mlsanity.com/paper/1901.01892/) (2019)
- [Probabilistic Anchor Assignment with IoU Prediction for Object Detection](https://mlsanity.com/paper/2007.08103/) (2020)
- [Learning to Assemble Neural Module Tree Networks for Visual Grounding](https://mlsanity.com/paper/1812.03299/) (2018)
- [Feature Selective Anchor-Free Module for Single-Shot Object Detection](https://mlsanity.com/paper/1903.00621/) (2019)
- [Imbalance Problems in Object Detection: A Review](https://mlsanity.com/paper/1909.00169/) (2019)

## Built on by (most cited first, 30 of 37)

- [DETRDistill: A Universal Knowledge Distillation Framework for DETR-families](https://mlsanity.com/paper/2211.10156/) (2022)
- [Plug and Play Active Learning for Object Detection](https://mlsanity.com/paper/2211.11612/) (2022)
- [Cascade-DETR: Delving into High-Quality Universal Object Detection](https://mlsanity.com/paper/2307.11035/) (2023)
- [PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection](https://mlsanity.com/paper/2211.10763/) (2022)
- [HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes](https://mlsanity.com/paper/2409.19833/) (2024)
- [Prediction-Guided Distillation for Dense Object Detection](https://mlsanity.com/paper/2203.05469/) (2022)
- [TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask](https://mlsanity.com/paper/2206.13381/) (2022)
- [VoxDet: Rethinking 3D Semantic Occupancy Prediction as Dense Object Detection](https://mlsanity.com/paper/2506.04623/) (2025)
- [Affine-Consistent Transformer for Multi-Class Cell Nuclei Detection](https://mlsanity.com/paper/2310.14154/) (2023)
- [Cell Graph Transformer for Nuclei Classification](https://mlsanity.com/paper/2402.12946/) (2024)
- [Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection](https://mlsanity.com/paper/2407.20078/) (2024)
- [SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving](https://mlsanity.com/paper/2305.06940/) (2023)
- [DenoDet: Attention as Deformable Multi-Subspace Feature Denoising for Target Detection in SAR Images](https://mlsanity.com/paper/2406.02833/) (2024)
- [Zone Evaluation: Revealing Spatial Bias in Object Detection](https://mlsanity.com/paper/2310.13215/) (2023)
- [Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection](https://mlsanity.com/paper/2509.20745/) (2025)
- [Source-Free Object Detection with Detection Transformer](https://mlsanity.com/paper/2510.11090/) (2025)
- [Task-Specific Context Decoupling for Object Detection](https://mlsanity.com/paper/2303.01047/) (2023)
- [Temporal Action Localization with Cross Layer Task Decoupling and Refinement](https://mlsanity.com/paper/2412.09202/) (2024)
- [Are Visual Recognition Models Robust to Image Compression?](https://mlsanity.com/paper/2304.04518/) (2023)
- [Faster OreFSDet : A Lightweight and Effective Few-shot Object Detector for Ore Images](https://mlsanity.com/paper/2305.01183/) (2023)
- [AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection](https://mlsanity.com/paper/2505.15184/) (2025)
- [DenoDet V2: Phase-Amplitude Cross Denoising for SAR Object Detection](https://mlsanity.com/paper/2508.09392/) (2025)
- [1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track](https://mlsanity.com/paper/2301.04796/) (2023)
- [Set-Based Face Recognition Beyond Disentanglement: Burstiness Suppression With Variance Vocabulary](https://mlsanity.com/paper/2304.06249/) (2023)
- [Prompt-based Grouping Transformer for Nucleus Detection and Classification](https://mlsanity.com/paper/2310.14176/) (2023)
- [Security Fence Inspection at Airports Using Object Detection](https://mlsanity.com/paper/2311.12064/) (2023)
- [FoRA: Low-Rank Adaptation Model beyond Multimodal Siamese Network](https://mlsanity.com/paper/2407.16129/) (2024)
- [CLIP-DQA: Blindly Evaluating Dehazed Images from Global and Local Perspectives Using CLIP](https://mlsanity.com/paper/2502.01707/) (2025)
- [Contrast-Guided Cross-Modal Distillation for Thermal Object Detection](https://mlsanity.com/paper/2511.01435/) (2025)
- [Caries DETR: Tooth Structure-aware Prior and Lesion-aware Dynamic Loss Refinement for DETR Based Caries Detection](https://mlsanity.com/paper/2604.23718/) (2026)

## Abstract (arXiv)

Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding. However, the current training pipeline for dense detectors is compromised to lots of conjunctions that may not hold. In this paper, we investigate three such important conjunctions: 1) only samples assigned as positive in classification head are used to train the regression head; 2) classification and regression share the same input feature and computational fields defined by the parallel head architecture; and 3) samples distributed in different feature pyramid layers are treated equally when computing the loss. We first carry out a series of pilot experiments to show disentangling such conjunctions can lead to persistent performance improvement. Then, based on these findings, we propose Disentangled Dense Object Detector (DDOD), in which simple and effective disentanglement mechanisms are designed and integrated into the current state-of-the-art dense object detectors. Extensive experiments on MS COCO benchmark show that our approach can lead to 2.0 mAP, 2.4 mAP and 2.2 mAP absolute improvements on RetinaNet, FCOS, and ATSS baselines with negligible extra overhead. Notably, our best model reaches 55.0 mAP on the COCO test-dev set and 93.5 AP on the hard subset of WIDER FACE, achieving new state-of-the-art performance on these two competitive benchmarks. Code is available at https://github.com/zehuichen123/DDOD.