CMS-RCNN: Contextual Multi-Scale Region-Based CNN for Unconstrained Face Detection

Abstract

Robust face detection in the wild is one of the ultimate components to support various facial related problems, i.e. unconstrained face recognition, facial periocular recognition, facial landmarking and pose estimation, facial expression recognition, 3D facial model construction, etc. Although the face detection problem has been intensely studied for decades with various commercial applications, it still meets problems in some real-world scenarios due to numerous challenges, e.g. heavy facial occlusions, extremely low resolutions, strong illumination, exceptionally pose variations, image or video compression artifacts, etc. In this paper, we present a face detection approach named Contextual Multi-Scale Region-based Convolution Neural Network (CMS-RCNN) to robustly solve the problems mentioned above. Similar to the region-based CNNs, our proposed network consists of the region proposal component and the region-of-interest (RoI) detection component. However, far apart of that network, there are two main contributions in our proposed network that play a significant role to achieve the state-of-theart performance in face detection. Firstly, the multi-scale information is grouped both in region proposal and RoI detection to deal with tiny face regions. Secondly, our proposed network allows explicit body contextual reasoning in the network inspired from the intuition of human vision system. The proposed approach is benchmarked on two recent challenging face detection databases, i.e. the WIDER FACE Dataset which contains high degree of variability, as well as the Face Detection Dataset and Benchmark (FDDB). The experimental results show that our proposed approach trained on WIDER FACE Dataset outperforms strong baselines on WIDER FACE Dataset by a large margin, and consistently achieves competitive results on FDDB against the recent state-of-the-art face detection methods.

Contextual Region-Based Convolutional Neural Network with Multilayer Fusion for SAR Ship Detection

“…In order to validate the effectiveness of the proposed method, Faster RCNN [15,38] and CMS-RCNN [29] are applied to Sentinel-1 dataset. CMS-RCNN, which has the same resolution as conv5, fuses conv3, con4 and conv5 by down-sampling.…”

“…Since such an operation simply reverses the forward and backward Due to the respective merits that different layers possess, multiple layers fusion is a popular way to enhance the performance of detection in the current top-performance detector. As CMS-RCNN [29] did, the first way is to integrate down-sampled earlier layers with the last layer of the sharing CNN. Despite the fact that the feature map information is increased, small-sized objects still only cause responses on a tiny area in a fused feature map.…”

“…The scale factor µ is able to be updated with the backpropagation and chain rule [29]. In this paper, a fixed scale factor, which makes the fused feature maps have the same mean level as the replaced layer in Faster RCNN, is adopted [28].…”

“…For instance, an object located on land is highly unlikely to be considered a ship, while an object with bright intensity in the ocean area is prone to be affirmed as a positive object. In order to mimic the visual effect of a human being in a computer vision field, context information is always added into the deep neural network to recognize the small-sized objects [27,29,33].…”

Recent advances in deep learning for object detection

“…Zhang et al[194] proposed FDNet based on ResNet with larger deformable convolutional kernels to capture image context. Zhu et al[195] proposed a Contextual Multi-Scale Region-based Convolution Neural Network (CMS-RCNN) in which multi-scale information was grouped both in region proposal and ROI detection to deal with faces at various range of scale. In addition, contextual information around faces is also considered in training detectors.…”