DenseNMT
Recently, neural machine translation has achieved remarkable progress by introducing well-designed deep neural networks into its encoder-decoder framework. From the optimization perspective, residual connections are adopted to improve learning performance for both encoder and decoder in most of these deep architectures, and advanced attention connections are applied as well. Inspired by the success of the DenseNet model in computer vision problems, in this paper, we propose a densely connected NMT architecture (DenseNMT) that is able to train more efficiently for NMT. The proposed DenseNMT not only allows dense connection in creating new features for both encoder and decoder, but also uses the dense attention structure to improve attention quality. Our experiments on multiple datasets show that DenseNMT structure is more competitive and efficient. …

VLocNet++
Visual localization is one of the fundamental enablers of robot autonomy which has been mostly tackled using local feature-based pipelines that efficiently encode knowledge about the environment and the underlying geometrical constraints. Although deep learning based approaches have shown considerable robustness in the context of significant perceptual changes, repeating structures and textureless regions, their performance has been subpar in comparison to local feature-based pipelines. In this paper, we propose the novel VLocNet++ architecture that attempts to overcome this limitation by simultaneously embedding geometric and semantic knowledge of the world into the pose regression network. We adopt a multitask learning approach that exploits the inter-task relationship between learning semantics, regressing 6-DoF global pose and odometry, for the mutual benefit of each of these tasks. VLocNet++ incorporates the Geometric Consistency Loss function that utilizes the predicted motion from the odometry stream to enforce global consistency during pose regression. Furthermore, we propose a self-supervised warping technique that uses the relative motion to warp intermediate network representations in the segmentation stream for learning consistent semantics. In addition, we propose a novel adaptive weighted fusion layer to leverage inter and intra task dependencies based on region activations. Finally, we introduce a first-of-a-kind urban outdoor localization dataset with pixel-level semantic labels and multiple loops for training deep networks. Extensive experiments on the challenging indoor Microsoft 7-Scenes benchmark and our outdoor DeepLoc dataset demonstrate that our approach exceeds the state-of-the-art, outperforming local feature-based methods while exhibiting substantial robustness in challenging scenarios. …

GOGGLES
Generating large labeled training data is becoming the biggest bottleneck in building and deploying supervised machine learning models. Recently, data programming has been proposed in the data management community to reduce the human cost in training data generation. Data programming expects users to write a set of labeling functions, each of which is a weak supervision source that labels a subset of data points with better-than-random accuracy. However, the success of data programming heavily depends on the quality (in terms of both accuracy and coverage) of the labeling functions that users still need to design manually. We propose affinity coding, a new paradigm for fully automatic generation of training data. In affinity coding, the similarity between the unlabeled instances and prototypes that are derived from the same unlabeled instances serve as signals (or sources of weak supervision) for determining class membership. We term this implicit similarity as the affinity score. Consequently, we can have as many sources of weak supervision as the number of unlabeled data points, without any human input. We also propose a system called GOGGLES that is an implementation of affinity coding for labeling image datasets. GOGGLES features novel techniques for deriving affinity scores from image datasets based on ‘semantic prototypes’ extracted from convolutional neural nets, as well as an expectation-maximization approach for performing class label inference based on the computed affinity scores. Compared to the state-of-the-art data programming system Snorkel, GOGGLES exhibits 14.88% average improvement in terms of the quality of labels generated for the binary labeling task. The GOGGLES system is open-sourced at https://…/. …

Pan-Sharpening Generative Adversarial Network (PSGAN)
Remote sensing image fusion (also known as pan-sharpening) aims to generate a high resolution multi-spectral image from inputs of a high spatial resolution single band panchromatic (PAN) image and a low spatial resolution multi-spectral (MS) image. In this paper, we propose PSGAN, a generative adversarial network (GAN) for remote sensing image pan-sharpening. To the best of our knowledge, this is the first attempt at producing high quality pan-sharpened images with GANs. The PSGAN consists of two parts. Firstly, a two-stream fusion architecture is designed to generate the desired high resolution multi-spectral images, then a fully convolutional network serving as a discriminator is applied to distinct ‘real’ or ‘pan-sharpened’ MS images. Experiments on images acquired by Quickbird and GaoFen-1 satellites demonstrate that the proposed PSGAN can fuse PAN and MS images effectively and significantly improve the results over the state of the art traditional and CNN based pan-sharpening methods. …