Object Detection via a Multi-region and Semantic Segmentation-Aware CNN Model

By Spyros Gidaris, Nikos Komodakis. 2015

773 citations recorded by the source corpus.

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.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Object Detection Networks on Convolutional Feature Maps (2015, methodology): “In recent detection systems [12], [13], [14], [23], [24], conv layers in the pre-trained models are thought of as region-independent feature extractors, and thus are shared on the entire image without being aware of the regions that are of interest.”
Cascade R-CNN: High Quality Object Detection and Instance Segmentation (2019, methodology): “n implemented by the proposed Cascade R-CNN, but ignores the problem of high-quality detection. Some explorations in multi-stage object detection have also been proposed. The multi-region detector of [17] introduced iterative bounding box regression, where a R-CNN is appliedseveral times to produce ”
You Only Look Once: Unified, Real-Time Object Detection (2015, methodology): “VOC 2012 test mAP aero bike bird boat bottle bus car cat chair cow table dog horse mbike personplant sheep sofa train tv MR CNN MORE DATA [11] 73.”
Beyond Skip Connections: Top-Down Modulation for Object Detection (2016, background): “Convolutional neural networks (ConvNets) have revolutionized the field of object detection [4, 14, 16, 17, 41, 44, 48].”
R-FCN: Object Detection via Region-based Fully Convolutional Networks (2016, methodology): “Following R-CNN [8], we adopt the popular two-stage object detection strategy [8, 9, 6, 7, 19, 1, 23] that consists of: (i) region proposal, and (ii) region classiﬁcation.”
Training Region-Based Object Detectors with Online Hard Example Mining (2016, methodology): “We adopt the multi-scale strategy from SPPnet [16] (and used by both FRCN [14] and MR-CNN [13]).”
Cascade R-CNN: Delving Into High Quality Object Detection (2017, methodology): “[10, 11, 18], and has somewhat unreliable gains.”
Hybrid Task Cascade for Instance Segmentation (2019, neutral): “Multi-region CNN [14] incorporates an iterative localization mechanism that alternates between box scoring and location refinement.”
A MultiPath Network for Object Detection (2016, methodology): “We also compare our foveal approach to the multiregion network [9] which used 10 regions (for a fair comparison, we re-implement it in our setup).”
Path Aggregation Network for Instance Segmentation (2018, methodology): “As shown in Table 1, our PANet with ResNet-50 trained on multi-scale images and tested on single-scale images already outperforms Mask R-CNN and the champion in 2016, where the latter used larger model ensembles and testing tricks of [23, 33, 10, 15, 39, 62].”
Proposal-Free Network for Instance-Level Object Segmentation (2015, neutral): “The detection pipelines [7] [24] [23] [5] generally start from”
Recent advances in convolutional neural networks (2015, methodology): “Beside R-CNN based methods, [137] proposes a multi-region and semantic segmentation-aware model for object detection.”