A residual networks family with hundreds or even thousands of layers dominates major image recognition tasks, but building a network by simply stacking residual blocks inevitably limits its optimization ability. This paper proposes a novel residual network architecture, residual networks of residual networks (RoR), to dig the optimization ability of residual networks. RoR substitutes optimizing residual mapping of residual mapping for optimizing original residual mapping. In particular, RoR adds levelwise shortcut connections upon original residual networks to promote the learning capability of residual networks. More importantly, RoR can be applied to various kinds of residual networks (ResNets, Pre-ResNets, and WRN) and significantly boost their performance. Our experiments demonstrate the effectiveness and versatility of RoR, where it achieves the best performance in all residual-network-like structures. Our RoR-3-WRN58-4 + SD models achieve new state-of-the-art results on CIFAR-10, CIFAR-100, and SVHN, with the test errors of 3.77%, 19.73%, and 1.59%, respectively. RoR-3 models also achieve state-of-the-art results compared with ResNets on the ImageNet data set.

Recent network research has demonstrated that the performance of convolutional neural networks can be improved by introducing a learning block that capture spatial correlations. In this work, we propose a novel Multiple Feature Reweight DenseNet (MFR-DenseNet) architecture. The MFR-DenseNet improves the representation power of the DenseNet by adaptively recalibrating the channel-wise feature responses and explicitly modeling the interdependencies between the features of different convolutional layers. First, in order to perform dynamic channel-wise feature recalibration, we construct the Channel Feature Reweight DenseNet (CFR-DenseNet) by introducing the Squeeze-and-Excitation Module (SEM) to DenseNet. Then, to model the interdependencies between the features of different convolutional layers, we propose the Double Squeeze-and-Excitation Module (DSEM) and construct the Inter-Layer Feature Reweight DenseNet (ILFR-DenseNet). In the last step, we designed the MFR-DenseNet by combining the CFR-DenseNet and the ILFR-DenseNet, with an ensemble learning approach. Our experiments demonstrate the effectiveness of CFR-DenseNet, ILFR-DenseNet, and MFR-DenseNet. More importantly, the MFRDenseNet drops the error rate on CIFAR-10 and CIFAR-100 by a large margin with significantly fewer parameters. Our 100-layer MFR-DenseNet (with 7.1M parameters) model achieves competitive results on CIFAR-10 and CIFAR-100 data sets, with test errors 3.57% and 18.27% respectively, achieving a 4.5% relative improvement on CIFAR-10 and a 5.09% relative improvement on CIFAR-100 over the best result of DenseNet (with 27.2M parameters).

The detection of insulators in power transmission and transformation inspection images is the basis for insulator state detection and fault diagnosis in thereafter. Aiming at the detection of insulators with different aspect ratios and scales and ones with mutual occlusion, a method of insulator inspection image based on the improved faster region-convolutional neural network (R-CNN) is put forward in this paper. By constructing a power transmission and transformation insulation equipment detection dataset and fine-tuning the faster R-CNN model, the anchor generation method and non-maximum suppression (NMS) in the region proposal network (RPN) of the faster R-CNN model were improved, thus realizing a better detection of insulators. The experimental results show that the average precision (AP) value of the faster R-CNN model was increased to 0.818 with the improved anchor generation method under the VGG-16 Net. In addition, the detection effect of different aspect ratios and different scales of insulators in the inspection images was improved significantly, and the occlusion of insulators could be effectively distinguished and detected using the improved NMS.

Automatically predicting age group and gender from face images acquired in unconstrained conditions is an important and challenging task in many real-world applications. Nevertheless, the conventional methods with manually-designed features on in-the-wild benchmarks are unsatisfactory because of incompetency to tackle large variations in unconstrained images. This difficulty is alleviated to some degree through convolutional neural networks (CNN) for its powerful feature representation. In this paper, we propose a new CNN-based method for age group and gender estimation leveraging residual networks of residual networks (RoR), which exhibits better optimization ability for age group and gender classification than other CNN architectures. Moreover, two modest mechanisms based on observation of the characteristics of age group are presented to further improve the performance of age estimation. In order to further improve the performance and alleviate over-fitting problem, RoR model is pre-trained on ImageNet first, and then it is fune-tuned on the IMDB-WIKI-101 data set for further learning the features of face images, finally, it is used to fine-tune on Adience data set. Our experiments illustrate the effectiveness of RoR method for age and gender estimation in the wild, where it achieves better performance than other CNN methods. Finally, the RoR-152+IMDB-WIKI-101 with two mechanisms achieves new state-of-the-art results on Adience benchmark.

Age estimation from a single face image has been an essential task in the field of human-computer interaction and computer vision, which has a wide range of practical application values. Accuracy of age estimation of face images in the wild is relatively low for existing methods, because they only take into account the global features, while neglecting the fine-grained features of age-sensitive areas. We propose a novel method based on our attention long short-term memory (AL) network for fine-grained age estimation in the wild, inspired by the fine-grained categories and the visual attention mechanism. This method combines the residual networks (ResNets) or the residual network of residual network (RoR) models with LSTM units to construct AL-ResNets or AL-RoR networks to extract local features of age-sensitive regions, which effectively improves the age estimation accuracy. First, a ResNets or a RoR model pretrained on ImageNet dataset is selected as the basic model, which is then fine-tuned on the IMDB-WIKI-101 dataset for age estimation. Then, we fine-tune the ResNets or the RoR on the target age datasets to extract the global features of face images. To extract the local features of age-sensitive regions, the LSTM unit is then presented to obtain the coordinates of the age-sensitive region automatically. Finally, the age group classification is conducted directly on the Adience dataset, and age-regression experiments are performed by the Deep EXpectation algorithm (DEX) on MORPH Album 2, FG-NET and 15/16LAP datasets. By combining the global and the local features, we obtain our final prediction results. Experimental results illustrate the effectiveness and robustness of the proposed AL-ResNets or AL-RoR for age estimation in the wild, where it achieves better state-of-the-art performance than all other convolutional neural network (CNN) methods on the Adience, MORPH Album 2, FG-NET and 15/16LAP datasets.

Insulator detection using an infrared image is challenged by variance of temperature, orientations, and a cluttered background. A robust and discriminative representation of insulators in electric power systems is needed. This paper proposes a novel method for generating this type of representation in infrared images by taking advantage of high-level discriminative Convolutional Neural Networks (CNNs) to feature the extraction framework and the deformation invariant nature of the Vector of Locally Aggregated Descriptors (VLAD) aggregator. Different from existing methods, we delve deep into the convolutional feature maps. We first extract deep activation maps from convolutional layers of a pretrained deep model and replace the last three fully-connected layers with a VLAD pooling layer to generate the representation of an insulator. Then, we train a Support Vector Machine (SVM) for binary classification. To further verify the effectiveness and robustness of our proposed feature, an insulator detection pipeline based on an object proposal is introduced. The experimental results show that our proposed method can achieve an accuracy of 93%. Meanwhile, the detection results demonstrate that our insulator detection pipeline has satisfied performance goals.