# LocNet: Improving Localization Accuracy for Object Detection

arXiv: https://arxiv.org/abs/1511.07763 · HTML: https://mlsanity.com/paper/1511.07763/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2015.

## Built on by (most cited first, 14 of 14)

- [PolyFormer: Referring Image Segmentation as Sequential Polygon Generation](https://mlsanity.com/paper/2302.07387/) (2023)
- [Focal and Efficient IOU Loss for Accurate Bounding Box Regression](https://mlsanity.com/paper/2101.08158/) (2021)
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021)
- [Localization Distillation for Object Detection](https://mlsanity.com/paper/2204.05957/) (2022)
- [RecNet: An Invertible Point Cloud Encoding through Range Image Embeddings for Multi-Robot Map Sharing and Reconstruction](https://mlsanity.com/paper/2402.02192/) (2024)
- [Phase-aggregated Dual-branch Network for Efficient Fingerprint Dense Registration](https://mlsanity.com/paper/2404.17159/) (2024)
- [Dense Hybrid Proposal Modulation for Lane Detection](https://mlsanity.com/paper/2304.14874/) (2023)
- [Bonsai: A Framework for Convolutional Neural Network Acceleration Using Criterion-Based Pruning](https://mlsanity.com/paper/2602.17145/) (2026)
- [Unified-IoU: For High-Quality Object Detection](https://mlsanity.com/paper/2408.06636/) (2024)
- [Object Detection Based Handwriting Localization](https://mlsanity.com/paper/2106.14989/) (2021)
- [Enhancing Fruit and Vegetable Detection in Unconstrained Environment with a Novel Dataset](https://mlsanity.com/paper/2409.13330/) (2024)
- [[Re] Network Deconvolution](https://mlsanity.com/paper/2410.01189/) (2024)
- [Text-guided Zero-Shot Object Localization](https://mlsanity.com/paper/2411.11357/) (2024)
- [Multispectral Detection Transformer with Infrared-Centric Feature Fusion](https://mlsanity.com/paper/2505.15137/) (2025)

## Abstract (arXiv)

We propose a novel object localization methodology with the purpose of boosting the localization accuracy of state-of-the-art object detection systems. Our model, given a search region, aims at returning the bounding box of an object of interest inside this region. To accomplish its goal, it relies on assigning conditional probabilities to each row and column of this region, where these probabilities provide useful information regarding the location of the boundaries of the object inside the search region and allow the accurate inference of the object bounding box under a simple probabilistic framework. For implementing our localization model, we make use of a convolutional neural network architecture that is properly adapted for this task, called LocNet. We show experimentally that LocNet achieves a very significant improvement on the mAP for high IoU thresholds on PASCAL VOC2007 test set and that it can be very easily coupled with recent state-of-the-art object detection systems, helping them to boost their performance. Finally, we demonstrate that our detection approach can achieve high detection accuracy even when it is given as input a set of sliding windows, thus proving that it is independent of box proposal methods.