Publications

@article{Kochupillai2020,
title = {Programming Away Human Rights and Responsibilities? “The Moral Machine Experiment” and the Need for a More “Humane” AV Future},
author = {Mrinalini Kochupillai and Christoph Lütge and Franziska Poszler},
url = {https://link.springer.com/article/10.1007/s11569-020-00374-4},
doi = {10.1007/S11569-020-00374-4/TABLES/2},
issn = {18714765},
year = {2020},
date = {2020-01-01},
journal = {NanoEthics},
volume = {14},
number = {3},
pages = {285-299},
publisher = {Springer Science and Business Media Deutschland GmbH},
abstract = {Dilemma situations involving the choice of which human life to save in the case of unavoidable accidents are expected to arise only rarely in the context of autonomous vehicles (AVs). Nonetheless, the scientific community has devoted significant attention to finding appropriate and (socially) acceptable automated decisions in the event that AVs or drivers of AVs were indeed to face such situations. Awad and colleagues, in their now famous paper “The Moral Machine Experiment”, used a “multilingual online ‘serious game’ for collecting large-scale data on how citizens would want AVs to solve moral dilemmas in the context of unavoidable accidents.” Awad and colleagues undoubtedly collected an impressive and philosophically useful data set of armchair intuitions. However, we argue that applying their findings to the development of “global, socially acceptable principles for machine learning” would violate basic tenets of human rights law and fundamental principles of human dignity. To make its arguments, our paper cites principles of tort law, relevant case law, provisions from the Universal Declaration of Human Rights, and rules from the German Ethics Code for Autonomous and Connected Driving.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{Mou2020d,
title = {ERA: A Dataset and Deep Learning Benchmark for Event Recognition in Aerial Videos},
author = {Lichao Mou and Yuansheng Hua and Pu Jin and Xiao Xiang Zhu and Senior Member},
url = {https://arxiv.org/abs/2001.11394v4},
doi = {10.48550/arxiv.2001.11394},
year = {2020},
date = {2020-01-01},
journal = {IEEE Geoscience and Remote Sensing Magazine},
abstract = {Along with the increasing use of unmanned aerial vehicles (UAVs), large
volumes of aerial videos have been produced. It is unrealistic for humans to
screen such big data and understand their contents. Hence methodological
research on the automatic understanding of UAV videos is of paramount
importance. In this paper, we introduce a novel problem of event recognition in
unconstrained aerial videos in the remote sensing community and present a
large-scale, human-annotated dataset, named ERA (Event Recognition in Aerial
videos), consisting of 2,864 videos each with a label from 25 different classes
corresponding to an event unfolding 5 seconds. The ERA dataset is designed to
have a significant intra-class variation and inter-class similarity and
captures dynamic events in various circumstances and at dramatically various
scales. Moreover, to offer a benchmark for this task, we extensively validate
existing deep networks. We expect that the ERA dataset will facilitate further
progress in automatic aerial video comprehension. The website is
https://lcmou.github.io/ERA_Dataset/},
note = {in press},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{Behrens2020,
title = {Neurally Augmented ALISTA},
author = {Freya Behrens and Jonathan Sauder and Peter Jung},
url = {https://arxiv.org/abs/2010.01930v1},
doi = {10.48550/arxiv.2010.01930},
year = {2020},
date = {2020-01-01},
abstract = {It is well-established that many iterative sparse reconstruction algorithms
can be unrolled to yield a learnable neural network for improved empirical
performance. A prime example is learned ISTA (LISTA) where weights, step sizes
and thresholds are learned from training data. Recently, Analytic LISTA
(ALISTA) has been introduced, combining the strong empirical performance of a
fully learned approach like LISTA, while retaining theoretical guarantees of
classical compressed sensing algorithms and significantly reducing the number
of parameters to learn. However, these parameters are trained to work in
expectation, often leading to suboptimal reconstruction of individual targets.
In this work we therefore introduce Neurally Augmented ALISTA, in which an LSTM
network is used to compute step sizes and thresholds individually for each
target vector during reconstruction. This adaptive approach is theoretically
motivated by revisiting the recovery guarantees of ALISTA. We show that our
approach further improves empirical performance in sparse reconstruction, in
particular outperforming existing algorithms by an increasing margin as the
compression ratio becomes more challenging.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{Hua2019,
title = {Relation Network for Multi-label Aerial Image Classification},
author = {Yuansheng Hua and Lichao Mou and Xiao Xiang Zhu},
url = {http://arxiv.org/abs/1907.07274 http://dx.doi.org/10.1109/TGRS.2019.2963364},
doi = {10.1109/TGRS.2019.2963364},
year = {2019},
date = {2019-01-01},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
volume = {58},
number = {7},
pages = {4558-4572},
publisher = {Institute of Electrical and Electronics Engineers Inc.},
abstract = {Multi-label classification plays a momentous role in perceiving intricate contents of an aerial image and triggers several related studies over the last years. However, most of them deploy few efforts in exploiting label relations, while such dependencies are crucial for making accurate predictions. Although an LSTM layer can be introduced to modeling such label dependencies in a chain propagation manner, the efficiency might be questioned when certain labels are improperly inferred. To address this, we propose a novel aerial image multi-label classification network, attention-aware label relational reasoning network. Particularly, our network consists of three elemental modules: 1) a label-wise feature parcel learning module, 2) an attentional region extraction module, and 3) a label relational inference module. To be more specific, the label-wise feature parcel learning module is designed for extracting high-level label-specific features. The attentional region extraction module aims at localizing discriminative regions in these features and yielding attentional label-specific features. The label relational inference module finally predicts label existences using label relations reasoned from outputs of the previous module. The proposed network is characterized by its capacities of extracting discriminative label-wise features in a proposal-free way and reasoning about label relations naturally and interpretably. In our experiments, we evaluate the proposed model on the UCM multi-label dataset and a newly produced dataset, AID multi-label dataset. Quantitative and qualitative results on these two datasets demonstrate the effectiveness of our model. To facilitate progress in the multi-label aerial image classification, the AID multi-label dataset will be made publicly available.},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{Yuinpress,
title = {SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images},
author = {Lichao Mou Yuansheng Hua Xiao Xiang Zhu Jane Wang Z in press. Tianze Yu Jianzhe Lin},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
keywords = {},
pubstate = {published},
tppubtype = {article}
}

@article{Kandala2022,
title = {Exploring Transformer and Multi-label Classification for Remote Sensing Image Captioning},
author = {Kandala, Hitesh and Saha, Sudipan and Banerjee, Biplab and Zhu, Xiao Xiang},
journal = {IEEE Geoscience and Remote Sensing Letters},
keywords = {.},
pubstate = {published},
tppubtype = {article}
}