Sort by: Year Popularity Relevance
Honglak Lee, Seunghoon Hong, Donggyun Kim, Wonkwang Lee - 2020
Learning disentangled representation of data without supervision is an important step towards improving the interpretability of generative models. Despite recent advances in disentangled representation learning, existing approaches often suffer from the trade-off between representation learning and generation performance i.e. improving generation...
Martha Larson, Zhuoran Liu, Zhengyu Zhao - 2020
We propose Adversarial Color Filtering (AdvCF), an approach that uses a differentiable color filter to create adversarial images. The color filter allows us to introduce large perturbations into images, while still maintaining or enhancing their photographic quality and appeal. AdvCF is motivated by properties that are necessary if adversarial im...
Yonghong Tian, Yongjian Wu, Baochang Zhang, Yuxin Zhang, Rongrong Ji, Mingbao Lin - 2020
Channel pruning is among the predominant approaches to compress deep neural networks. To this end, most existing pruning methods focus on selecting channels (filters) by importance/optimization or regularization based on rule-of-thumb designs, which defects in sub-optimal pruning. In this paper, we propose a new channel pruning method based on ar...
Sophie M. Fosson - 2020
The development of online algorithms to track time-varying systems has drawn a lot of attention in the last years, in particular in the framework of online convex optimization. Meanwhile, sparse time-varying optimization has emerged as a powerful tool to deal with widespread applications, ranging from dynamic compressed sensing to parsimonious sy...
H. Li, J. Peng, X. Mei, B. Yin, T. Xu, S. Chen, X. Chen - 2020
Traditional online maps, widely used on Internet such as Google map and Baidu map, are rendered from vector data. Timely updating online maps from vector data, of which the generating is time-consuming, is a difficult mission. It is a shortcut to generate online maps in time from remote sensing images, which can be acquired timely without vector ...
Matthias Schubert, Michael Fromm, Evgeniy Faerman, Max Berrendorf, Hitansh Singla, Viet Tran, Valentyn Melnychuk, Diana Davletshina - 2020
Obtaining labels for medical (image) data requires scarce and expensive experts. Moreover, due to ambiguous symptoms, single images rarely suffice to correctly diagnose a medical condition. Instead, it often requires to take additional background information such as the patient's medical history or test results into account. Hence, instead of foc...
Alexandre Xavier Falcão, João Paulo Papa, Gustavo Henrique de Rosa - 2020
Machine learning techniques have been paramount throughout the last years, being applied in a wide range of tasks, such as classification, object recognition, person identification, image segmentation, among others. Nevertheless, conventional classification algorithms, e.g., Logistic Regression, Decision Trees, Bayesian classifiers, might lack co...
Jimeng Sun, Lucas M. Glass, Wen Tang, Yasha Wang, Cao Xiao, Junyi Gao - 2020
Deep learning has demonstrated success in health risk prediction especially for patients with chronic and progressing conditions. Most existing works focus on learning disease Network (StageNet) model to extract disease stage information from patient data and integrate it into risk prediction. StageNet is enabled by (1) a stage-aware long short-t...
Minlie Huang, Xiaoyan Zhu, Zhihao Zhao, Fei Huang, Jian Guan - 2020
Story generation, namely generating a reasonable story from a leading context, is an important but challenging task. In spite of the success in modeling fluency and local coherence, existing neural language generation models (e.g., GPT-2) still suffer from repetition, logic conflicts, and lack of long-range coherence in generated stories. We conj...
Alexander M. Rush - 2020
The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning frameworks. We introduce Torch-Struct, a library for structured prediction designed to take advantage of and integrate...
