Going Deeper with Convolutions
This paper presents a deep convolutional neural network architecture codenamed Inception. This newly designed architecture enhance the utilization of the computing resources by increasing the depth and width of the network while maintaining the computational budget constant. The optimization of the model was achieved by the Hebbian principle (Footnote 1) and the intuition of multi-scale processing. The proposed architecture was implemented through a 22 layers deep network called GoogLeNet and significantly outperformed the state of the art in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
The current architecture is built on the network-in-network approach proposed by Lin et al. . They added additional 1 X 1 convolutional layers, serving as dimension reduction modules to significantly reduce the number of parameters of the model. The paper also took inspiration from the Regions with Convolutional Neural Networks (R-CNN) proposed by Girshick et al. . The overall detection problem is divided into two subproblems: to first utilize low-level cues for potential object proposals, and to then use CNN to classify object categories.
The performance of deep neural networks can be improved by increasing the depth and the width of the networks. However, this suffers two major bottlenecks. One disadvantage is that the enlarged network tends to overfit the train data, especially if there is only limited labeled examples. The other drawback is the dramatic increase in computational resources when learning large number of parameters.
The fundamental way of handling both problems would be to use sparsely connected instead of fully connected networks and, at the same time, make numerical calculation on non-uniform sparse data structures efficient. Therefore, the inception architecture was motivated by Arora et al.  and Catalyurek et al.  and overcome these difficulties by clustering sparse matrices into relatively dense submatrices. It takes advantage of both extra sparsity and existing computational hardware.
The Inception architecture consists of stacking blocks called the inception modules. The idea is that to increase the depth and width of model by finding local optimal sparse structure and repeating it spatially. Traditionally, in each layer of convolutional network pooling operation and convolution and its size (1 by 1, 3 by 3 or 5 by 5) should be decided while all of them are beneficial for the modeling power of the network. Whereas, in Inception module instead of choosing, all these various options are computed simultaneously (Fig. 1a). Inspired by layer-by-layer construction of Arora et al. , in Inception module statistics correlation of the last layer is analyzed and clustered into groups of units with high correlation. These clusters form units of next layer and are connected to the units of previous layer. Each unit from the earlier layer corresponds to some region of the input image and the outputs of them are concatenated into a filter bank. Additionally, because of the beneficial effect of pooling in the convolutional networks, a parallel path of pooling has been added in each module. The Inception module in its naïve form (Fig. 1a) suffers from high computation and power cost. In addition, as the concatenated output from the various convolutions and the pooling layer will be an extremely deep channel of output volume, the claim that this architecture has an improved memory and computation power use looks like counterintuitive. However, this issue has been addressed by adding a 1 by 1 convolution before costly 3 by 3 and 5 by 5 convolutions. The idea of 1 by 1 convolution was first introduced by Lin et al. and called network in network . This 1x1 convolution mathematically is equivalent to a multilayer perceptron which reduces the dimension of filter space (the depth of the output volume) and on top of that they also act as a non-linear rectifying activation layer ReLu to add to the non-linearity immediately after each 1 by 1 convolution (Fig. 1b). This enables less over-fitting due to smaller Kernel size (1 by 1). This distinctive dimensionality reduction feature of the 1 by 1 convolution allows shielding of the large number of input filters of the previous stage to the next stage (Footnote 2).
The combination of various layers of convolution has some similarity with human eyes in interpreting the visual information in a sense that human eyes also process the visual information at various scale and combines to extract the features from different scale simultaneously. Similarly, in inception design network in network designs extract the fine grain details of input volume while medium- and large-sized filters cover a large receptive field of the inputs and extract their features and with pooling operations overfitting can be overcome by reducing the spatial sizes.
ILSVRC 2014 Challenge Results:
The proposed architecture was implemented through a deep network called GoogLeNet as a submission for ILSVRC14’s Classification Challenge and Detection Challenge.
The classification challenge is to classify images into one of 1000 categories in the Imagenet hierarchy. The top-5 error rate - the percentage of test examples for which the correct class is not in the top 5 predicted classes - is used for measuring accuracy. The final submission of GoogLeNet obtains a top-5 error of 6.67% on both the validation and testing data, ranking first among all participants, significantly outperforming top teams in previous years, and not utilizing external data.
The ILSVRC detection challenge asks to produce bounding boxes around objects in images among 200 classes. Detected objects count as correct if they match the class of the groundtruth and their bounding boxes overlap by at least 50%. Each image may contain multiple objects (with different scales) or none. The mean average precision (mAP) is used to report performance. Using the Inception model as a region classifier, combining Selective Search and using an ensemble of 6 CNNs, GoogLeNet gave top detection results, almost doubling accuracy of the the 2013 top model.
Googlenet outperformed the other previous deep learning networks, and it became a proof of concept that approximating the expected optimal sparse structure by readily available dense building blocks (or the inception modules) is a viable method for improving the neural networks in computer vision. Even without performing any bounding box operations to detect objects, this architecture gained a significant amount of quality with a modest amount of computational resources.
The paper's contributions towards patterning unordered network outputs and using associative embeddings for connecting vertices and edges are commendable. However, it should be noted this paper is only an incremental improvement over existing well-studied architectures like the hour glass architecture. The modifications also seem to be hacky. The authors say that they make a slight modification to the hourglass design and double the number of features and weight all the loses equally. No scientific justification for why this is needed is given. Also the choice of constants to be 3 and 6 for [math] s_o[/math] and [math] s_r[/math] is not clear, as the authors leave out a fraction of the cases. I am not sure if the changes made are truly a critical advance as the experiments are conducted only on a single dataset and no generalizability arguments are made by the authors. So the methods might just work well only for this dataset and the changes may pertain to only this one. The theoretical analysis done in the paper comes directly from the hourglass literature and cannot be accounted for novelty.
Appendix 1: Sample Outputs
Appendix 2: Stacked Hourglass Architecture
Although this goes beyond the focus of the paper, I would like to add a brief overview of the stacked hourglass architecture used to generate the heat map. This architecture is unique in that it allows cyclical top-down, bottom-up inference and recombination of features. While most architectures focus on optimizing the bottom-up portion (reducing dimensionality), the stacked-hourglass gives the network more flexibility in how it generates a representation by allowing it to learn a series of down-sampling / up-sampling steps.
1. Alejandro Newell and Jia Deng, “Pixels to Graphs by Associative Embedding,” in NIPS, 2017
2. Alejandro Newell, Kaiyu Yang, and Jia Deng. Stacked Hourglass Networks for Human Pose Estimation. ECCV, 2016
3. Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. NIPS, pages 91–99, 2015.