Sort by: Year Popularity Relevance
Margarida Carvalho, Mostafa ElAraby, Guy Wolf - 2020
We introduce a novel approach to optimize the architecture of deep neural networks by identifying critical neurons and removing non-critical ones. The proposed approach utilizes a mixed integer programming (MIP) formulation of neural models which includes a continuous importance score computed for each neuron in the network. The optimization in MIP...
Eyke Hüllermeier, Marcel Wever, Alexander Tornede - 2020
Algorithm selection (AS) deals with selecting an algorithm from a fixed set of candidate algorithms most suitable for a specific instance of an algorithmic problem, e.g., choosing solvers for SAT problems. Benchmark suites for AS usually comprise candidate sets consisting of at most tens of algorithms, whereas in combined algorithm selection and ...
Jie Zhou, Cheng Niu, Yang Feng, Jinchao Zhang, Zongjia Li, Zekang Li - 2020
Audio-Visual Scene-Aware Dialog (AVSD) is a task to generate responses when chatting about a given video, which is organized as a track of the 8th Dialog System Technology Challenge (DSTC8). To solve the task, we propose a universal multimodal transformer and introduce the multi-task learning method to learn joint representations among different ...
Hsin-Min Wang, Yu Tsao, Yu-Huai Peng, Chen-Chou Lo, Hsin-Te Hwang, Hao Luo, Wen-Chin Huang - 2020
An effective approach for voice conversion (VC) is to disentangle linguistic content from other components in the speech signal. The effectiveness of variational autoencoder (VAE) based VC (VAE-VC), for instance, strongly relies on this principle. In our prior work, we proposed a cross-domain VAE-VC (CDVAE-VC) framework, which utilized acoustic f...
Anton Konushin, Olga Barinova, Ilia Petrov, Konstantin Sofiiuk - 2020
Deep neural networks have become a mainstream approach to interactive segmentation. As we show in our experiments, while for some images a trained network provides accurate segmentation result with just a few clicks, for some unknown objects it cannot achieve satisfactory result even with a large amount of user input. Recently proposed backpropag...
German Rigau, Rodrigo Agerri, Iker García - 2020
This paper presents a new technique for creating monolingual and cross-lingual meta-embeddings. Our method integrates multiple word embeddings created from complementary techniques, textual sources, knowledge bases and languages. Existing word vectors are projected to a common semantic space using linear transformations and averaging. With our me...
Steve Renals, Peter Bell, Chau Luu - 2020
Many recent works on deep speaker embeddings train their feature extraction networks on large classification tasks, distinguishing between all speakers in a training set. Empirically, this has been shown to produce speaker-discriminative embeddings, even for unseen speakers. However, it is not clear that this is the optimal means of training embe...
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...
Iryna Gurevych, Claire Gardent, Yue Zhang, Leonardo F. R. Ribeiro - 2020
Recent graph-to-text models generate text from graph-based data using either global or local aggregation to learn node representations. Global node encoding allows explicit communication between two distant nodes, thereby neglecting graph topology as all nodes are connected. In contrast, local node encoding considers the relations between directl...
Lei Du, Yingyu Lin, Chengkun Lang, Shixian Ning, Zhuang Liu1, Huiwei Zhou - 2020
Protein-protein interaction (PPI) extraction from published scientific literature provides additional support for precision medicine efforts. However, many of the current PPI extraction methods need extensive feature engineering and cannot make full use of the prior knowledge in knowledge bases (KB). KBs contain huge amounts of structured informa...
