Over the recent years, there has been an increasing interest in large-scale classification of remote sensing images. In this context, the Inria Aerial Image Labeling Benchmark has been released online in December 2016. In this paper, we discuss the outcomes of the first year of the benchmark contest, which consisted in dense labeling of aerial images into building / not building classes, covering areas of five cities not present in the training set. We present four methods with the highest numerical accuracies, all four being convolutional neural network approaches. It is remarkable that three of these methods use the U-net architecture, which has thus proven to become a new standard in image dense labeling.

No abstract

No abstract

Consistency-based semi-supervised learning methods such as the Mean Teacher method are state-of-the-art on image datasets, but have yet to be applied to audio data. Such methods encourage model predictions to be consistent on perturbed input data. In this paper, we incorporate audio-specific perturbations into the Mean Teacher algorithm and demonstrate the effectiveness of the resulting method on audio classification tasks. Specifically, we perturb audio inputs by mixing in other environmental audio clips, and leverage other training examples as sources of noise. Experiments on the Google Speech Command Dataset and UrbanSound8K Dataset show that the method can achieve comparable performance to a purely supervised approach while using only a fraction of the labels.

Polarization maintaining optical fiber (PMOF) is a kind of special optical fiber that is designed to transmit the linearly polarized light. Unlike the general optical fiber, it is critical to conduct the rotational alignment between two PMOFs to guarantee the efficiency of light transmission. Until now, this alignment task still cannot be addressed with an efficient and economical way. Hence, we propose a monolithically integrated two-axis flexure-based microgripper that has the grasping and rubbing functions. To achieve a compact structure, the microgripper is designed with an asymmetric architecture. In this paper, the pseudo-rigid body model approach and finite element analysis are conducted to provide the essential guideline to accomplish the theoretical design. The prototype is fabricated by wire electrical discharge machining, with which two experiments are conducted to validate the performance of the microgripper. The experimental results demonstrate that the proposed microgripper can firmly grasp the optical fiber with the diameter of 250 μm and meanwhile can rub it more than 90° accurately and effectively, which indicate that it can satisfy the operating requirements well in the PMOF assembly.