# Auto-Context R-CNN

Source: [Auto-Context R-CNN](<https://www.sota2.com/research/paper/68fa64861e209131cea0526f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:06:03.000Z

Authors: Bo Li, Tianfu Wu, Lun Zhang, Rufeng Chu

Published: 2018-07-08T15:45:28.000Z

## Abstract

Region-based convolutional neural networks (R-CNN)~\\cite{fast\_rcnn,faster\_rcnn,mask\_rcnn} have largely dominated object detection. Operators defined on RoIs (Region of Interests) play an important role in R-CNNs such as RoIPooling~\\cite{fast\_rcnn} and RoIAlign~\\cite{mask\_rcnn}. They all only utilize information inside RoIs for RoI prediction, even with their recent deformable extensions~\\cite{deformable\_cnn}. Although surrounding context is well-known for its importance in object detection, it has yet been integrated in R-CNNs in a flexible and effective way. Inspired by the auto-context work~\\cite{auto\_context} and the multi-class object layout work~\\cite{nms\_context}, this paper presents a generic context-mining RoI operator (i.e., \\textit{RoICtxMining}) seamlessly integrated in R-CNNs, and the resulting object detection system is termed \\textbf{Auto-Context R-CNN} which is trained end-to-end. The proposed RoICtxMining operator is a simple yet effective two-layer extension of the RoIPooling or RoIAlign operator. Centered at an object-RoI, it creates a $3\\times 3$ layout to mine contextual information adaptively in the $8$ surrounding context regions on-the-fly. Within each of the $8$ context regions, a context-RoI is mined in term of discriminative power and its RoIPooling / RoIAlign features are concatenated with the object-RoI for final prediction. \\textit{The proposed Auto-Context R-CNN is robust to occlusion and small objects, and shows promising vulnerability for adversarial attacks without being adversarially-trained.} In experiments, it is evaluated using RoIPooling as the backbone and shows competitive results on Pascal VOC, Microsoft COCO, and KITTI datasets (including $6.9\\%$ mAP improvements over the R-FCN~\\cite{rfcn} method on COCO \\textit{test-dev} dataset and the first place on both KITTI pedestrian and cyclist detection as of this submission).

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1807.02842>)

[PDF](<https://arxiv.org/pdf/1807.02842.pdf>)