Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains well with an initial learning rate 1.0, and easily generalizes to different tasks. We enforce scale invariance with local statistics in the data to align similar samples at diverse scales. To accelerate convergence, we enforce a GL(n)-invariance property with global statistics extracted from a batch such that the gradient descent solution should remain invariant under basis change. Profiling analysis shows our proposed modifications takes 5% of the computations of the underlying convolution layer. Tested on convolutional networks and transformer networks, our proposed technique requires fewer iterations to train, surpasses all baselines by a large margin, seamlessly works on both small and large batch size training, and applies to different computer vision and language tasks.

We present an unsupervised learning pipeline for dense depth, optical flow and egomotion estimation for autonomous driving applications, using the event-based output of the Dynamic Vision Sensor (DVS) as input. The backbone of our pipeline is a bioinspired encoder-decoder neural network architecture - ECN. To train the pipeline, we introduce a covariance normalization technique which resembles the lateral inhibition mechanism found in animal neural systems.Our work is the first monocular pipeline that generates dense depth and optical flow from sparse event data only, and is able to transfer from day to night scenes without any additional training. The network works in self-supervised mode and has just 150k parameters. We evaluate our pipeline on the MVSEC self driving dataset and present results for depth, optical flow and and egomotion estimation. Thanks to the efficient design, we are able to achieve inference rates of 300 FPS on a single Nvidia 1080Ti GPU. Our experiments demonstrate significant improvements upon works that used deep learning on event data, as well as the ability to perform well during both day and night.

We present the first event-based learning approach for motion segmentation in indoor scenes and the first event-based dataset - EV-IMO- which includes accurate pixel-wise motion masks, egomotion and ground truth depth. Our approach is based on an efficient implementation of the SfM learning pipeline using a low parameter neural network architecture on event data. In addition to camera egomotion and a dense depth map, the network estimates independently moving object segmentation at the pixel-level and computes per-object 3D translational velocities of moving objects. We also train a shallow network with just 40k parameters, which is able to compute depth and egomotion. Our EV-IMO dataset features 32 minutes of indoor recording with up to 3 fast moving objects in the camera field of view. The objects and the camera are tracked using a VICON®motion capture system. By 3D scanning the room and the objects, ground truth of the depth map and pixel-wise object masks are obtained. We then train and evaluate our learning pipeline on EV-IMO and demonstrate that it is well suited for scene constrained robotics applications. SUPPLEMENTARY MATERIAL The supplementary video, code, trained models, appendix and a dataset will be made available at http://prg.cs.umd.edu/EV-IMO.html.

We introduce Evenly Cascaded convolutional Network (ECN), a neural network taking inspiration from the cascade algorithm of wavelet analysis. ECN employs two feature streams - a low-level and high-level steam. At each layer these streams interact, such that low-level features are modulated using advanced perspectives from the high-level stream. ECN is evenly structured through resizing feature map dimensions by a consistent ratio, which removes the burden of ad-hoc specification of feature map dimensions. ECN produces easily interpretable features maps, a result whose intuition can be understood in the context of scale-space theory. We demonstrate that ECN's design facilitates the training process through providing easily trainable shortcuts. We report new state-of-the-art results for small networks, without the need for additional treatment such as pruning or compression - a consequence of ECN's simple structure and direct training. A 6-layered ECN design with under 500k parameters achieves 95.24% and 78.99% accuracy on CIFAR-10 and CIFAR-100 datasets, respectively, outperforming the current state-of-the-art on small parameter networks, and a 3 million parameter ECN produces results competitive to the state-of-the-art.

For robots that have the capability to interact with the physical environment through their end effectors, understanding the surrounding scenes is not merely a task of image classification or object recognition. To perform actual tasks, it is critical for the robot to have a functional understanding of the visual scene. Here, we address the problem of localization and recognition of functional areas in an arbitrary indoor scene, formulated as a two-stage deep learning based detection pipeline. A new scene functionality testing-bed, which is compiled from two publicly available indoor scene datasets, is used for evaluation. Our method is evaluated quantitatively on the new dataset, demonstrating the ability to perform efficient recognition of functional areas from arbitrary indoor scenes. We also demonstrate that our detection model can be generalized to novel indoor scenes by cross validating it with images from two different datasets.

LightNet is a lightweight, versatile, purely Matlab-based deep learning framework. The idea underlying its design is to provide an easy-to-understand, easy-to-use and efficient computational platform for deep learning research. The implemented framework supports major deep learning architectures such as Multilayer Perceptron Networks (MLP), Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). The framework also supports both CPU and GPU computation, and the switch between them is straightforward. Different applications in computer vision, natural language processing and robotics are demonstrated as experiments.

Abstract Motivation: Base-calling of sequencing data produced by high-throughput sequencing platforms is a fundamental process in current bioinformatics analysis. However, existing third-party probabilistic or machine-learning methods that significantly improve the accuracy of base-calls on these platforms are impractical for production use due to their computational inefficiency. Results: We directly formulate base-calling as a blind deconvolution problem and implemented BlindCall as an efficient solver to this inverse problem. BlindCall produced base-calls at accuracy comparable to state-of-the-art probabilistic methods while processing data at rates 10 times faster in most cases. The computational complexity of BlindCall scales linearly with read length making it better suited for new long-read sequencing technologies. Availability and Implementation: BlindCall is implemented as a set of Matlab scripts available for download at http://cbcb.umd.edu/∼hcorrada/secgen. Contact: [email protected]

As Semantic Web technologies mature and new releases of key elements, such as SPARQL 1.1 and OWL 2.0, become available, the Life Sciences continue to push the boundaries of these technologies with ever more sophisticated tools and applications. Unsurprisingly, therefore, interest in the SWAT4LS (Semantic Web Applications and Tools for the Life Sciences) activities have remained high, as was evident during the third international SWAT4LS workshop held in Berlin in December 2010. Contributors to this workshop were invited to submit extended versions of their papers, the best of which are now made available in the special supplement of BMC Bioinformatics. The papers reflect the wide range of work in this area, covering the storage and querying of Life Sciences data in RDF triple stores, tools for the development of biomedical ontologies and the semantics-based integration of Life Sciences as well as clinicial data.

We present here a prototype of an algorithm for vehicle speed estimation. Different from previous approaches, our algorithm requires no road markers and fewer manual calibrations. Based on specific projection rules, we find a relation between the in-camera coordinate and the real world coordinate. A non-linear regression is employed to estimate the model parameters. This model enables us to estimate the real world position of the vehicles directly from a video sequence taken by a surveillance camera. The algorithm shows its ability to produce accurate estimations in our experiments.