# Object detection via a multi-region & semantic segmentation-aware CNN model

arXiv: https://arxiv.org/abs/1505.01749 · HTML: https://mlsanity.com/paper/1505.01749/

## Key facts

- Cited by 47 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2015.

## Built on by (most cited first, 30 of 47)

- [Pre-Trained Models: Past, Present and Future](https://mlsanity.com/paper/2106.07139/) (2021)
- [RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2103.10039/) (2021)
- [Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark](https://mlsanity.com/paper/2206.13996/) (2022)
- [Large-Scale Unsupervised Object Discovery](https://mlsanity.com/paper/2106.06650/) (2021)
- [Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection](https://mlsanity.com/paper/2304.08876/) (2023)
- [Sequential End-to-end Network for Efficient Person Search](https://mlsanity.com/paper/2103.10148/) (2021)
- [Rank-based Decomposable Losses in Machine Learning: A Survey](https://mlsanity.com/paper/2207.08768/) (2022)
- [Sum of Ranked Range Loss for Supervised Learning](https://mlsanity.com/paper/2106.03300/) (2021)
- [Recurrent Glimpse-based Decoder for Detection with Transformer](https://mlsanity.com/paper/2112.04632/) (2021)
- [Active Learning Strategies for Weakly-supervised Object Detection](https://mlsanity.com/paper/2207.12112/) (2022)
- [Hallucination In Object Detection -- A Study In Visual Part Verification](https://mlsanity.com/paper/2106.02523/) (2021)
- [Progressive Pretext Task Learning for Human Trajectory Prediction](https://mlsanity.com/paper/2407.11588/) (2024)
- [Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection](https://mlsanity.com/paper/2110.15017/) (2021)
- [Certifiably Robust Interpretation via Renyi Differential Privacy](https://mlsanity.com/paper/2107.01561/) (2021)
- [Boosting R-CNN: Reweighting R-CNN Samples by RPN's Error for Underwater Object Detection](https://mlsanity.com/paper/2206.13728/) (2022)
- [CenterNet++ for Object Detection](https://mlsanity.com/paper/2204.08394/) (2022)
- [CE-FPN: Enhancing Channel Information for Object Detection](https://mlsanity.com/paper/2103.10643/) (2021)
- [3D Cascade RCNN: High Quality Object Detection in Point Clouds](https://mlsanity.com/paper/2211.08248/) (2022)
- [PrObeD: Proactive Object Detection Wrapper](https://mlsanity.com/paper/2310.18788/) (2023)
- [CRFace: Confidence Ranker for Model-Agnostic Face Detection Refinement](https://mlsanity.com/paper/2103.07017/) (2021)
- [EResFD: Rediscovery of the Effectiveness of Standard Convolution for Lightweight Face Detection](https://mlsanity.com/paper/2204.01209/) (2022)
- [Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection](https://mlsanity.com/paper/2207.06603/) (2022)
- [Spatio-Temporal Point Process for Multiple Object Tracking](https://mlsanity.com/paper/2302.02444/) (2023)
- [VISLIX: An XAI Framework for Validating Vision Models with Slice Discovery and Analysis](https://mlsanity.com/paper/2505.03132/) (2025)
- [Towards Full-to-Empty Room Generation with Structure-Aware Feature Encoding and Soft Semantic Region-Adaptive Normalization](https://mlsanity.com/paper/2112.05396/) (2021)
- [Evaluating Context for Deep Object Detectors](https://mlsanity.com/paper/2205.02887/) (2022)
- [AMD: Adaptive Masked Distillation for Object Detection](https://mlsanity.com/paper/2301.13538/) (2023)
- [Improving Apparel Detection with Category Grouping and Multi-grained Branches](https://mlsanity.com/paper/2101.06770/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [Frame Fusion with Vehicle Motion Prediction for 3D Object Detection](https://mlsanity.com/paper/2306.10699/) (2023)

## Abstract (arXiv)

We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting CNN-based representation aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization. We exploit the above properties of our recognition module by integrating it on an iterative localization mechanism that alternates between scoring a box proposal and refining its location with a deep CNN regression model. Thanks to the efficient use of our modules, we detect objects with very high localization accuracy. On the detection challenges of PASCAL VOC2007 and PASCAL VOC2012 we achieve mAP of 78.2% and 73.9% correspondingly, surpassing any other published work by a significant margin.