Christian Szegedy

Convolutional networks are at the core of most state of-the-art computer vision solutions for a wide variety of tasks. Since 2014 very deep convolutional networks started to become mainstream, yielding substantial gains in various benchmarks. Although increased model size and computational cost tend to translate to immediate quality gains for most tasks (as long as enough labeled data is provided for training), computational efficiency and low parameter count are still enabling factors for various use cases such as mobile vision and big-data scenarios. Here we are exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization. We benchmark our methods on the ILSVRC 2012 classification challenge validation set demonstrate substantial gains over the state of the art: 21:2% top-1 and 5:6% top-5 error for single frame evaluation using a network with a computational cost of 5 billion multiply-adds per inference and with using less than 25 million parameters. With an ensemble of 4 models and multi-crop evaluation, we report 3:5% top-5 error and 17:3% top-1 error on the validation set and 3:6% top-5 error on the official test set.

We present a method for detecting objects in images us-ing a single deep neural network. Our approach, named SSD, discretizes the output space of bounding boxes into a set of bounding box priors over different aspect ratios and scales per feature map location. At prediction time, the network generates confidences that each prior corre-sponds to objects of interest and produces adjustments to the prior to better match the object shape. Additionally, the network combines predictions from multiple feature maps with different resolutions to naturally handle objects of var-ious sizes. Our SSD model is simple relative to methods that requires object proposals, such as R-CNN and Multi-Box, because it completely discards the proposal generation step and encapsulates all the computation in a single net-work. This makes SSD easy to train and straightforward to integrate into systems that require a detection component. Experimental results on ILSVRC DET and PASCAL VOC dataset confirm that SSD has comparable performance with methods that utilize an additional object proposal step and yet is 100-1000 × faster. Compared to other single stage methods, SSD has similar or better performance, while pro-viding a unified framework for both training and inference. 1.

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.