Beihang University

About: Beihang University is a education organization based out in Beijing, China. It is known for research contribution in the topics: Computer science & Control theory. The organization has 67002 authors who have published 73507 publications receiving 975691 citations. The organization is also known as: Beijing University of Aeronautics and Astronautics.

Mimicking Very Efficient Network for Object Detection

Abstract: Current CNN based object detectors need initialization from pre-trained ImageNet classification models, which are usually time-consuming. In this paper, we present a fully convolutional feature mimic framework to train very efficient CNN based detectors, which do not need ImageNet pre-training and achieve competitive performance as the large and slow models. We add supervision from high-level features of the large networks in training to help the small network better learn object representation. More specifically, we conduct a mimic method for the features sampled from the entire feature map and use a transform layer to map features from the small network onto the same dimension of the large network. In training the small network, we optimize the similarity between features sampled from the same region on the feature maps of both networks. Extensive experiments are conducted on pedestrian and common object detection tasks using VGG, Inception and ResNet. On both Caltech and Pascal VOC, we show that the modified 2.5× accelerated Inception network achieves competitive performance as the full Inception Network. Our faster model runs at 80 FPS for a 1000×1500 large input with only a minor degradation of performance on Caltech.

Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints

Abstract: Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage of correlations between co-occurring labels and visual input but risk inadvertently encoding social biases found in web corpora. In this work, we study data and models associated with multilabel object classification and visual semantic role labeling. We find that (a) datasets for these tasks contain significant gender bias and (b) models trained on these datasets further amplify existing bias. For example, the activity cooking is over 33% more likely to involve females than males in a training set, and a trained model further amplifies the disparity to 68% at test time. We propose to inject corpus-level constraints for calibrating existing structured prediction models and design an algorithm based on Lagrangian relaxation for collective inference. Our method results in almost no performance loss for the underlying recognition task but decreases the magnitude of bias amplification by 47.5% and 40.5% for multilabel classification and visual semantic role labeling, respectively.

Patterning of controllable surface wettability for printing techniques

Abstract: Patterning of controllable surface wettability has attracted wide scientific attention due to its importance in both fundamental research and practical applications. In particular, it is crucial to form clear image areas and non-image areas in printing techniques based on wetting and dewetting. This review summarizes the recent research on and applications of patterning of controllable surface wettability for printing techniques, with a focus on the design and fabrication of the precise surface wettability patterning by enhancing the contrast of hydrophilicity and hydrophobicity, such as superhydrophilicity and superhydrophobicity. The selected topics mainly include patterned surface wettability for lithographic printing with different plate-making techniques, patterned surface wettability for microcontact printing with a patterned wetting stamp and special wettability mediated patterning microtransfer printing, patterned surface wettability for inkjet printing with controllable surface wettability of the substrate and printing head to ink, and patterned surface wettability by a combination of different printing techniques. A personal perspective on the future development and remaining challenges of this research is also briefly discussed.