# Rethinking Classification and Localization for Object Detection

arXiv: https://arxiv.org/abs/1904.06493 · HTML: https://mlsanity.com/paper/1904.06493/

## Key facts

- Cited by 98 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Apr 2019.

## Built on by (most cited first, 30 of 98)

- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS](https://mlsanity.com/paper/2304.00501/) (2023)
- [DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection](https://mlsanity.com/paper/2108.09017/) (2021)
- [Anchor-free Oriented Proposal Generator for Object Detection](https://mlsanity.com/paper/2110.01931/) (2021)
- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [Focal and Efficient IOU Loss for Accurate Bounding Box Regression](https://mlsanity.com/paper/2101.08158/) (2021)
- [SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection](https://mlsanity.com/paper/2403.06534/) (2024)
- [Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image](https://mlsanity.com/paper/2108.09368/) (2021)
- [Disentangle Your Dense Object Detector](https://mlsanity.com/paper/2107.02963/) (2021)
- [SparseTT: Visual Tracking with Sparse Transformers](https://mlsanity.com/paper/2205.03776/) (2022)
- [COCO-O: A Benchmark for Object Detectors under Natural Distribution Shifts](https://mlsanity.com/paper/2307.12730/) (2023)
- [Real-time Object Detection for Streaming Perception](https://mlsanity.com/paper/2203.12338/) (2022)
- [ESTextSpotter: Towards Better Scene Text Spotting with Explicit Synergy in Transformer](https://mlsanity.com/paper/2308.10147/) (2023)
- [Semantics-Guided Contrastive Network for Zero-Shot Object detection](https://mlsanity.com/paper/2109.06062/) (2021)
- [An Economic Framework for 6-DoF Grasp Detection](https://mlsanity.com/paper/2407.08366/) (2024)
- [Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection](https://mlsanity.com/paper/2106.06072/) (2021)
- [AFPN: Asymptotic Feature Pyramid Network for Object Detection](https://mlsanity.com/paper/2306.15988/) (2023)
- [Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection](https://mlsanity.com/paper/2501.03775/) (2025)
- [HEAD: HEtero-Assists Distillation for Heterogeneous Object Detectors](https://mlsanity.com/paper/2207.05345/) (2022)
- [You Should Look at All Objects](https://mlsanity.com/paper/2207.07889/) (2022)
- [A DeNoising FPN With Transformer R-CNN for Tiny Object Detection](https://mlsanity.com/paper/2406.05755/) (2024)
- [Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotations](https://mlsanity.com/paper/2206.00274/) (2022)
- [Mutual Supervision for Dense Object Detection](https://mlsanity.com/paper/2109.05986/) (2021)
- [Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection](https://mlsanity.com/paper/2206.13728/) (2022)
- [Object Detection in Hyperspectral Image via Unified Spectral-Spatial Feature Aggregation](https://mlsanity.com/paper/2306.08370/) (2023)
- [FoodLogoDet-1500: A Dataset for Large-Scale Food Logo Detection via Multi-Scale Feature Decoupling Network](https://mlsanity.com/paper/2108.04644/) (2021)
- [Deep Structured Instance Graph for Distilling Object Detectors](https://mlsanity.com/paper/2109.12862/) (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)
- [SalienDet: A Saliency-based Feature Enhancement Algorithm for Object Detection for Autonomous Driving](https://mlsanity.com/paper/2305.06940/) (2023)

## Abstract (arXiv)

Two head structures (i.e. fully connected head and convolution head) have been widely used in R-CNN based detectors for classification and localization tasks. However, there is a lack of understanding of how does these two head structures work for these two tasks. To address this issue, we perform a thorough analysis and find an interesting fact that the two head structures have opposite preferences towards the two tasks. Specifically, the fully connected head (fc-head) is more suitable for the classification task, while the convolution head (conv-head) is more suitable for the localization task. Furthermore, we examine the output feature maps of both heads and find that fc-head has more spatial sensitivity than conv-head. Thus, fc-head has more capability to distinguish a complete object from part of an object, but is not robust to regress the whole object. Based upon these findings, we propose a Double-Head method, which has a fully connected head focusing on classification and a convolution head for bounding box regression. Without bells and whistles, our method gains +3.5 and +2.8 AP on MS COCO dataset from Feature Pyramid Network (FPN) baselines with ResNet-50 and ResNet-101 backbones, respectively.