A commercial robot, trained by its manufacturer to recognize a predefined number and type of objects, might be used in many settings, that will in general differ in their illumination conditions, background, type and degree of clutter, and so on. Recent computer vision works tackle this generalization issue through domain adaptation methods, assuming as source the visual domain where the system is trained and as target the domain of deployment. All approaches assume to have access to images from all classes of the target during training, an unrealistic condition in robotics applications. We address this issue proposing an algorithm that takes into account the specific needs of robot vision. Our intuition is that the nature of the domain shift experienced mostly in robotics is local. We exploit this through the learning of maps that spatially ground the domain and quantify the degree of shift, embedded into an end-to-end deep domain adaptation architecture. By explicitly localizing the roots of the domain shift we significantly reduce the number of parameters of the architecture to tune, we gain the flexibility necessary to deal with subset of categories in the target domain at training time, and we provide a clear feedback on the rationale behind any classification decision, which can be exploited in human-robot interactions. Experiments on two different settings of the iCub World database confirm the suitability of our method for robot vision.
Expressive efficiency refers to the relation between two architectures A and B, whereby any function realized by B could be replicated by A, but there exists functions realized by A, which cannot be replicated by B unless its size grows significantly larger. For example, it is known that deep networks are exponentially efficient with respect to shallow networks, in the sense that a shallow network must grow exponentially large in order to approximate the functions represented by a deep network of polynomial size. In this work, we extend the study of expressive efficiency to the attribute of network connectivity and in particular to the effect of "overlaps" in the convolutional process, i.e., when the stride of the convolution is smaller than its filter size (receptive field). To theoretically analyze this aspect of network's design, we focus on a well-established surrogate for ConvNets called Convolutional Arithmetic Circuits (ConvACs), and then demonstrate empirically that our results hold for standard ConvNets as well. Specifically, our analysis shows that having overlapping local receptive fields, and more broadly denser connectivity, results in an exponential increase in the expressive capacity of neural networks. Moreover, while denser connectivity can increase the expressive capacity, we show that the most common types of modern architectures already exhibit exponential increase in expressivity, without relying on fully-connected layers.
Cell counting is a ubiquitous, yet tedious task that would greatly benefit from automation. From basic biological questions to clinical trials, cell counts provide key quantitative feedback that drive research. Unfortunately, cell counting is most commonly a manual task and can be time-intensive. The task is made even more difficult due to overlapping cells, existence of multiple focal planes, and poor imaging quality, among other factors. Here, we describe a convolutional neural network approach, using a recently described feature pyramid network combined with a VGG-style neural network, for segmenting and subsequent counting of cells in a given microscopy image.
In recent years, there have been several works that use website fingerprinting techniques to enable a local adversary to determine which website a Tor user visits. While the current state-of-the-art attack, which uses deep learning, outperforms prior art with medium to large amounts of data, it attains marginal to no accuracy improvements when both use small amounts of training data. In this work, we propose Var-CNN, a website fingerprinting attack that leverages deep learning techniques along with novel insights specific to packet sequence classification. In open-world settings with large amounts of data, Var-CNN attains over $1\%$ higher true positive rate (TPR) than state-of-the-art attacks while achieving $4\times$ lower false positive rate (FPR). Var-CNN's improvements are especially notable in low-data scenarios, where it reduces the FPR of prior art by $3.12\%$ while increasing the TPR by $13\%$. Overall, insights used to develop Var-CNN can be applied to future deep learning based attacks, and substantially reduce the amount of training data needed to perform a successful website fingerprinting attack. This shortens the time needed for data collection and lowers the likelihood of having data staleness issues.
Tree species identification using bark images is a challenging problem that could prove useful for many forestry related tasks. However, while the recent progress in deep learning showed impressive results on standard vision problems, a lack of datasets prevented its use on tree bark species classification. In this work, we present, and make publicly available, a novel dataset called BarkNet 1.0 containing more than 23,000 high-resolution bark images from 23 different tree species over a wide range of tree diameters. With it, we demonstrate the feasibility of species recognition through bark images, using deep learning. More specifically, we obtain an accuracy of 93.88% on single crop, and an accuracy of 97.81% using a majority voting approach on all of the images of a tree. We also empirically demonstrate that, for a fixed number of images, it is better to maximize the number of tree individuals in the training database, thus directing future data collection efforts.
Semantic segmentation of robotic instruments is an important problem for the robot-assisted surgery. One of the main challenges is to correctly detect an instrument's position for the tracking and pose estimation in the vicinity of surgical scenes. Accurate pixel-wise instrument segmentation is needed to address this challenge. In this paper we describe our winning solution for MICCAI 2017 Endoscopic Vision SubChallenge: Robotic Instrument Segmentation. Our approach demonstrates an improvement over the state-of-the-art results using several novel deep neural network architectures. It addressed the binary segmentation problem, where every pixel in an image is labeled as an instrument or background from the surgery video feed. In addition, we solve a multi-class segmentation problem, where we distinguish different instruments or different parts of an instrument from the background. In this setting, our approach outperforms other methods in every task subcategory for automatic instrument segmentation thereby providing state-of-the-art solution for this problem. The source code for our solution is made publicly available at https://github.com/ternaus/robot-surgery-segmentation
The newsvendor problem is one of the most basic and widely applied inventory models. There are numerous extensions of this problem. If the probability distribution of the demand is known, the problem can be solved analytically. However, approximating the probability distribution is not easy and is prone to error; therefore, the resulting solution to the newsvendor problem may be not optimal. To address this issue, we propose an algorithm based on deep learning that optimizes the order quantities for all products based on features of the demand data. Our algorithm integrates the forecasting and inventory-optimization steps, rather than solving them separately, as is typically done, and does not require knowledge of the probability distributions of the demand. Numerical experiments on real-world data suggest that our algorithm outperforms other approaches, including data-driven and machine learning approaches, especially for demands with high volatility. Finally, in order to show how this approach can be used for other inventory optimization problems, we provide an extension for (r,Q) policies.
Tensor2Tensor is a library for deep learning models that is well-suited for neural machine translation and includes the reference implementation of the state-of-the-art Transformer model.
Designing an incentive compatible auction that maximizes expected revenue is an intricate task. The single-item case was resolved in a seminal piece of work by Myerson in 1981, but more than 40 years later a full analytical understanding of the optimal design still remains elusive for settings with two or more items. In this work, we initiate the exploration of the use of tools from deep learning for the automated design of optimal auctions. We model an auction as a multi-layer neural network, frame optimal auction design as a constrained learning problem, and show how it can be solved using standard machine learning pipelines. In addition to providing generalization bounds, we present extensive experimental results, recovering essentially all known solutions that come from the theoretical analysis of optimal auction design problems and obtaining novel mechanisms for settings in which the optimal mechanism is unknown.
RANSAC is an important algorithm in robust optimization and a central building block for many computer vision applications. In recent years, traditionally hand-crafted pipelines have been replaced by deep learning pipelines, which can be trained in an end-to-end fashion. However, RANSAC has so far not been used as part of such deep learning pipelines, because its hypothesis selection procedure is non-differentiable. In this work, we present two different ways to overcome this limitation. The most promising approach is inspired by reinforcement learning, namely to replace the deterministic hypothesis selection by a probabilistic selection for which we can derive the expected loss w.r.t. to all learnable parameters. We call this approach DSAC, the differentiable counterpart of RANSAC. We apply DSAC to the problem of camera localization, where deep learning has so far failed to improve on traditional approaches. We demonstrate that by directly minimizing the expected loss of the output camera poses, robustly estimated by RANSAC, we achieve an increase in accuracy. In the future, any deep learning pipeline can use DSAC as a robust optimization component.
We introduce the use of rectified linear units (ReLU) as the classification function in a deep neural network (DNN). Conventionally, ReLU is used as an activation function in DNNs, with Softmax function as their classification function. However, there have been several studies on using a classification function other than Softmax, and this study is an addition to those. We accomplish this by taking the activation of the penultimate layer $h_{n - 1}$ in a neural network, then multiply it by weight parameters $\theta$ to get the raw scores $o_{i}$. Afterwards, we threshold the raw scores $o_{i}$ by $0$, i.e. $f(o) = \max(0, o_{i})$, where $f(o)$ is the ReLU function. We provide class predictions $\hat{y}$ through argmax function, i.e. argmax $f(x)$.
High Efficiency Video Coding (HEVC) significantly reduces bit-rates over the proceeding H.264 standard but at the expense of extremely high encoding complexity. In HEVC, the quad-tree partition of coding unit (CU) consumes a large proportion of the HEVC encoding complexity, due to the bruteforce search for rate-distortion optimization (RDO). Therefore, this paper proposes a deep learning approach to predict the CU partition for reducing the HEVC complexity at both intra- and inter-modes, which is based on convolutional neural network (CNN) and long- and short-term memory (LSTM) network. First, we establish a large-scale database including substantial CU partition data for HEVC intra- and inter-modes. This enables deep learning on the CU partition. Second, we represent the CU partition of an entire coding tree unit (CTU) in the form of a hierarchical CU partition map (HCPM). Then, we propose an early-terminated hierarchical CNN (ETH-CNN) for learning to predict the HCPM. Consequently, the encoding complexity of intra-mode HEVC can be drastically reduced by replacing the brute-force search with ETH-CNN to decide the CU partition. Third, an early-terminated hierarchical LSTM (ETH-LSTM) is proposed to learn the temporal correlation of the CU partition. Then, we combine ETH-LSTM and ETH-CNN to predict the CU partition for reducing the HEVC complexity for inter-mode. Finally, experimental results show that our approach outperforms other state-of-the-art approaches in reducing the HEVC complexity at both intra- and inter-modes.
Malware is constantly adapting in order to avoid detection. Model based malware detectors, such as SVM and neural networks, are vulnerable to so-called adversarial examples which are modest changes to detectable malware that allows the resulting malware to evade detection. Continuous-valued methods that are robust to adversarial examples of images have been developed using saddle-point optimization formulations. We are inspired by them to develop similar methods for the discrete, e.g. binary, domain which characterizes the features of malware. A specific extra challenge of malware is that the adversarial examples must be generated in a way that preserves their malicious functionality. We introduce methods capable of generating functionally preserved adversarial malware examples in the binary domain. Using the saddle-point formulation, we incorporate the adversarial examples into the training of models that are robust to them. We evaluate the effectiveness of the methods and others in the literature on a set of Portable Execution~(PE) files. Comparison prompts our introduction of an online measure computed during training to assess general expectation of robustness.
Deep learning continues to push state-of-the-art performance for the semantic segmentation of color (i.e., RGB) imagery; however, the lack of annotated data for many remote sensing sensors (i.e. hyperspectral imagery (HSI)) prevents researchers from taking advantage of this recent success. Since generating sensor specific datasets is time intensive and cost prohibitive, remote sensing researchers have embraced deep unsupervised feature extraction. Although these methods have pushed state-of-the-art performance on current HSI benchmarks, many of these tools are not readily accessible to many researchers. In this letter, we introduce a software pipeline, which we call EarthMapper, for the semantic segmentation of non-RGB remote sensing imagery. It includes self-taught spatial-spectral feature extraction, various standard and deep learning classifiers, and undirected graphical models for post-processing. We evaluated EarthMapper on the Indian Pines and Pavia University datasets and have released this code for public use.
Image reconstruction under multiple light scattering is crucial in a number of applications such as diffraction tomography. The reconstruction problem is often formulated as a nonconvex optimization, where a nonlinear measurement model is used to account for multiple scattering and regularization is used to enforce prior constraints on the object. In this paper, we propose a powerful alternative to this optimization-based view of image reconstruction by designing and training a deep convolutional neural network that can invert multiple scattered measurements to produce a high-quality image of the refractive index. Our results on both simulated and experimental datasets show that the proposed approach is substantially faster and achieves higher imaging quality compared to the state-of-the-art methods based on optimization.
Quantifying behavior is crucial for many applications in neuroscience. Videography provides easy methods for the observation and recording of animal behavior in diverse settings, yet extracting particular aspects of a behavior for further analysis can be highly time consuming. In motor control studies, humans or other animals are often marked with reflective markers to assist with computer-based tracking, yet markers are intrusive (especially for smaller animals), and the number and location of the markers must be determined a priori. Here, we present a highly efficient method for markerless tracking based on transfer learning with deep neural networks that achieves excellent results with minimal training data. We demonstrate the versatility of this framework by tracking various body parts in a broad collection of experimental settings: mice odor trail-tracking, egg-laying behavior in drosophila, and mouse hand articulation in a skilled forelimb task. For example, during the skilled reaching behavior, individual joints can be automatically tracked (and a confidence score is reported). Remarkably, even when a small number of frames are labeled ($\approx 200$), the algorithm achieves excellent tracking performance on test frames that is comparable to human accuracy.
Deep Learning Library (DLL) is a new library for machine learning with deep neural networks that focuses on speed. It supports feed-forward neural networks such as fully-connected Artificial Neural Networks (ANNs) and Convolutional Neural Networks (CNNs). It also has very comprehensive support for Restricted Boltzmann Machines (RBMs) and Convolutional RBMs. Our main motivation for this work was to propose and evaluate novel software engineering strategies with potential to accelerate runtime for training and inference. Such strategies are mostly independent of the underlying deep learning algorithms. On three different datasets and for four different neural network models, we compared DLL to five popular deep learning frameworks. Experimentally, it is shown that the proposed framework is systematically and significantly faster on CPU and GPU. In terms of classification performance, similar accuracies as the other frameworks are reported.
In this work we detail a novel open source library, called MMLSpark, that combines the flexible deep learning library Cognitive Toolkit, with the distributed computing framework Apache Spark. To achieve this, we have contributed Java Language bindings to the Cognitive Toolkit, and added several new components to the Spark ecosystem. In addition, we also integrate the popular image processing library OpenCV with Spark, and present a tool for the automated generation of PySpark wrappers from any SparkML estimator and use this tool to expose all work to the PySpark ecosystem. Finally, we provide a large library of tools for working and developing within the Spark ecosystem. We apply this work to the automated classification of Snow Leopards from camera trap images, and provide an end to end solution for the non-profit conservation organization, the Snow Leopard Trust.
Identifying coordinate transformations that make strongly nonlinear dynamics approximately linear is a central challenge in modern dynamical systems. These transformations have the potential to enable prediction, estimation, and control of nonlinear systems using standard linear theory. The Koopman operator has emerged as a leading data-driven embedding, as eigenfunctions of this operator provide intrinsic coordinates that globally linearize the dynamics. However, identifying and representing these eigenfunctions has proven to be mathematically and computationally challenging. This work leverages the power of deep learning to discover representations of Koopman eigenfunctions from trajectory data of dynamical systems. Our network is parsimonious and interpretable by construction, embedding the dynamics on a low-dimensional manifold that is of the intrinsic rank of the dynamics and parameterized by the Koopman eigenfunctions. In particular, we identify nonlinear coordinates on which the dynamics are globally linear using a modified auto-encoder. We also generalize Koopman representations to include a ubiquitous class of systems that exhibit continuous spectra, ranging from the simple pendulum to nonlinear optics and broadband turbulence. Our framework parametrizes the continuous frequency using an auxiliary network, enabling a compact and efficient embedding at the intrinsic rank, while connecting our models to half a century of asymptotics. In this way, we benefit from the power and generality of deep learning, while retaining the physical interpretability of Koopman embeddings.
As neural networks grow deeper and wider, learning networks with hard-threshold activations is becoming increasingly important, both for network quantization, which can drastically reduce time and energy requirements, and for creating large integrated systems of deep networks, which may have non-differentiable components and must avoid vanishing and exploding gradients for effective learning. However, since gradient descent is not applicable to hard-threshold functions, it is not clear how to learn networks of them in a principled way. We address this problem by observing that setting targets for hard-threshold hidden units in order to minimize loss is a discrete optimization problem, and can be solved as such. The discrete optimization goal is to find a set of targets such that each unit, including the output, has a linearly separable problem to solve. Given these targets, the network decomposes into individual perceptrons, which can then be learned with standard convex approaches. Based on this, we develop a recursive mini-batch algorithm for learning deep hard-threshold networks that includes the popular but poorly justified straight-through estimator as a special case. Empirically, we show that our algorithm improves classification accuracy in a number of settings, including for AlexNet and ResNet-18 on ImageNet, when compared to the straight-through estimator.