M. Andreetto

Bio: M. Andreetto is an academic researcher from Google. The author has contributed to research in topics: Image segmentation & Object detection. The author has an hindex of 10, co-authored 17 publications receiving 10293 citations. Previous affiliations of M. Andreetto include University of Padua & California Institute of Technology.

MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications

Abstract: We present a class of efficient models called MobileNets for mobile and embedded vision applications. MobileNets are based on a streamlined architecture that uses depth-wise separable convolutions to build light weight deep neural networks. We introduce two simple global hyper-parameters that efficiently trade off between latency and accuracy. These hyper-parameters allow the model builder to choose the right sized model for their application based on the constraints of the problem. We present extensive experiments on resource and accuracy tradeoffs and show strong performance compared to other popular models on ImageNet classification. We then demonstrate the effectiveness of MobileNets across a wide range of applications and use cases including object detection, finegrain classification, face attributes and large scale geo-localization.

3D Reconstruction by Shadow Carving: Theory and Practical Evaluation

Abstract: Cast shadows are an informative cue to the shape of objects. They are particularly valuable for discovering object's concavities which are not available from other cues such as occluding boundaries. We propose a new method for recovering shape from shadows which we call shadow carving. Given a conservative estimate of the volume occupied by an object, it is possible to identify and carve away regions of this volume that are inconsistent with the observed pattern of shadows. We prove a theorem that guarantees that when these regions are carved away from the shape, the shape still remains conservative. Shadow carving overcomes limitations of previous studies on shape from shadows because it is robust with respect to errors in shadows detection and it allows the reconstruction of objects in the round, rather than just bas-reliefs. We propose a reconstruction system to recover shape from silhouettes and shadow carving. The silhouettes are used to reconstruct the initial conservative estimate of the object's shape and shadow carving is used to carve out the concavities. We have simulated our reconstruction system with a commercial rendering package to explore the design parameters and assess the accuracy of the reconstruction. We have also implemented our reconstruction scheme in a table-top system and present the results of scanning of several objects.

Automatic 3D modeling of textured cultural heritage objects

Abstract: A widespread use of three-dimensional (3D) models in cultural heritage application requires low cost equipment and technically simple modeling procedures. In this context, methods for automatic 3D modeling of textured objects can play a central role. Such methods need fully automatic techniques for 3D view registration and for the removal of texture artifacts. The paper proposes an image processing based procedure that is very robust and simple. It does not require special equipment or skill in order to make textured 3D models. These proposals, originally conceived to address the cost issues of cultural heritage modeling, can be profitably exploited also in other modeling applications.

3D registration by textured spin-images

Abstract: This work is motivated by the desire of exploiting for 3D registration purposes the photometric information current range cameras typically associate to range data. Automatic pairwise 3D registration procedures are two steps procedures with the first step performing an automatic crude estimate of the rigid motion parameters and the second step refining them by the ICP algorithm or some of its variations. Methods for efficiently implementing the first crude automatic estimate are still an open research area. Spin-images are a 3D matching technique very effective in this task. Since spin-images solely exploit geometry information it appears natural to extend their original definition to include texture information. Such an operation can clearly be made in many ways. This work introduces one particular extension of spin-images, called textured spin-images, and demonstrates its performance for 3D registration. It will be seen that textured spin-images enjoy remarkable properties since they can give rigid motion estimates more robust, more precise, more resilient to noise than standard spin-images at a lower computational cost.

Efficient Convolutional Neural Networks and Techniques to Reduce Associated Computational Costs

Abstract: The present disclosure provides systems and methods to reduce computational costs associated with convolutional neural networks. In addition, the present disclosure provides a class of efficient models termed “MobileNets” for mobile and embedded vision applications. MobileNets are based on a straight-forward architecture that uses depthwise separable convolutions to build light weight deep neural networks. The present disclosure further provides two global hyper-parameters that efficiently trade-off between latency and accuracy. These hyper-parameters allow the entity building the model to select the appropriately sized model for the particular application based on the constraints of the problem. MobileNets and associated computational cost reduction techniques are effective across a wide range of applications and use cases.

Squeeze-and-Excitation Networks

Abstract: The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy. In this work, we focus instead on the channel relationship and propose a novel architectural unit, which we term the “Squeeze-and-Excitation” (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. We further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost. Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2.251 percent, surpassing the winning entry of 2016 by a relative improvement of ${\sim }$ ∼ 25 percent. Models and code are available at https://github.com/hujie-frank/SENet .

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Abstract: In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe efficient ways of applying these mobile models to object detection in a novel framework we call SSDLite. Additionally, we demonstrate how to build mobile semantic segmentation models through a reduced form of DeepLabv3 which we call Mobile DeepLabv3. is based on an inverted residual structure where the shortcut connections are between the thin bottleneck layers. The intermediate expansion layer uses lightweight depthwise convolutions to filter features as a source of non-linearity. Additionally, we find that it is important to remove non-linearities in the narrow layers in order to maintain representational power. We demonstrate that this improves performance and provide an intuition that led to this design. Finally, our approach allows decoupling of the input/output domains from the expressiveness of the transformation, which provides a convenient framework for further analysis. We measure our performance on ImageNet [1] classification, COCO object detection [2], VOC image segmentation [3]. We evaluate the trade-offs between accuracy, and number of operations measured by multiply-adds (MAdd), as well as actual latency, and the number of parameters.

MobileNetV2: Inverted Residuals and Linear Bottlenecks

Abstract: In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes. We also describe efficient ways of applying these mobile models to object detection in a novel framework we call SSDLite. Additionally, we demonstrate how to build mobile semantic segmentation models through a reduced form of DeepLabv3 which we call Mobile DeepLabv3. The MobileNetV2 architecture is based on an inverted residual structure where the input and output of the residual block are thin bottleneck layers opposite to traditional residual models which use expanded representations in the input an MobileNetV2 uses lightweight depthwise convolutions to filter features in the intermediate expansion layer. Additionally, we find that it is important to remove non-linearities in the narrow layers in order to maintain representational power. We demonstrate that this improves performance and provide an intuition that led to this design. Finally, our approach allows decoupling of the input/output domains from the expressiveness of the transformation, which provides a convenient framework for further analysis. We measure our performance on Imagenet classification, COCO object detection, VOC image segmentation. We evaluate the trade-offs between accuracy, and number of operations measured by multiply-adds (MAdd), as well as the number of parameters

Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation

Abstract: Spatial pyramid pooling module or encode-decoder structure are used in deep neural networks for semantic segmentation task. The former networks are able to encode multi-scale contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple effective fields-of-view, while the latter networks can capture sharper object boundaries by gradually recovering the spatial information. In this work, we propose to combine the advantages from both methods. Specifically, our proposed model, DeepLabv3+, extends DeepLabv3 by adding a simple yet effective decoder module to refine the segmentation results especially along object boundaries. We further explore the Xception model and apply the depthwise separable convolution to both Atrous Spatial Pyramid Pooling and decoder modules, resulting in a faster and stronger encoder-decoder network. We demonstrate the effectiveness of the proposed model on PASCAL VOC 2012 and Cityscapes datasets, achieving the test set performance of 89% and 82.1% without any post-processing. Our paper is accompanied with a publicly available reference implementation of the proposed models in Tensorflow at https://github.com/tensorflow/models/tree/master/research/deeplab.

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Abstract: Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available. In this paper, we systematically study model scaling and identify that carefully balancing network depth, width, and resolution can lead to better performance. Based on this observation, we propose a new scaling method that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient. We demonstrate the effectiveness of this method on scaling up MobileNets and ResNet. To go even further, we use neural architecture search to design a new baseline network and scale it up to obtain a family of models, called EfficientNets, which achieve much better accuracy and efficiency than previous ConvNets. In particular, our EfficientNet-B7 achieves state-of-the-art 84.3% top-1 accuracy on ImageNet, while being 8.4x smaller and 6.1x faster on inference than the best existing ConvNet. Our EfficientNets also transfer well and achieve state-of-the-art accuracy on CIFAR-100 (91.7%), Flowers (98.8%), and 3 other transfer learning datasets, with an order of magnitude fewer parameters. Source code is at this https URL.