Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Topic": models, code, and papers

Fair Attribute Classification through Latent Space De-biasing

Dec 04, 2020
Vikram V. Ramaswamy, Sunnie S. Y. Kim, Olga Russakovsky

Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world. Models trained from data in which target labels are correlated with protected attributes (e.g., gender, race) are known to learn and exploit those correlations. In this work, we introduce a method for training accurate target classifiers while mitigating biases that stem from these correlations. We use GANs to generate realistic-looking images, and perturb these images in the underlying latent space to generate training data that is balanced for each protected attribute. We augment the original dataset with this perturbed generated data, and empirically demonstrate that target classifiers trained on the augmented dataset exhibit a number of both quantitative and qualitative benefits. We conduct a thorough evaluation across multiple target labels and protected attributes in the CelebA dataset, and provide an in-depth analysis and comparison to existing literature in the space.

* Code can be found at https://github.com/princetonvisualai/gan-debiasing 

  Access Paper or Ask Questions

CovidExplorer: A Multi-faceted AI-based Search and Visualization Engine for COVID-19 Information

Nov 30, 2020
Heer Ambavi, Kavita Vaishnaw, Udit Vyas, Abhisht Tiwari, Mayank Singh

The entire world is engulfed in the fight against the COVID-19 pandemic, leading to a significant surge in research experiments, government policies, and social media discussions. A multi-modal information access and data visualization platform can play a critical role in supporting research aimed at understanding and developing preventive measures for the pandemic. In this paper, we present a multi-faceted AI-based search and visualization engine, CovidExplorer. Our system aims to help researchers understand current state-of-the-art COVID-19 research, identify research articles relevant to their domain, and visualize real-time trends and statistics of COVID-19 cases. In contrast to other existing systems, CovidExplorer also brings in India-specific topical discussions on social media to study different aspects of COVID-19. The system, demo video, and the datasets are available at http://covidexplorer.in.

* 4 pages, 7 figures, The associated system can be accessed at http://covidexplorer.in, To be published in the Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM '20) (October 19-23, 2020)(Virtual Event, Ireland) 

  Access Paper or Ask Questions

Deep Learning based Monocular Depth Prediction: Datasets, Methods and Applications

Nov 09, 2020
Qing Li, Jiasong Zhu, Jun Liu, Rui Cao, Qingquan Li, Sen Jia, Guoping Qiu

Estimating depth from RGB images can facilitate many computer vision tasks, such as indoor localization, height estimation, and simultaneous localization and mapping (SLAM). Recently, monocular depth estimation has obtained great progress owing to the rapid development of deep learning techniques. They surpass traditional machine learning-based methods by a large margin in terms of accuracy and speed. Despite the rapid progress in this topic, there are lacking of a comprehensive review, which is needed to summarize the current progress and provide the future directions. In this survey, we first introduce the datasets for depth estimation, and then give a comprehensive introduction of the methods from three perspectives: supervised learning-based methods, unsupervised learning-based methods, and sparse samples guidance-based methods. In addition, downstream applications that benefit from the progress have also been illustrated. Finally, we point out the future directions and conclude the paper.


  Access Paper or Ask Questions

Knowledge Distillation for BERT Unsupervised Domain Adaptation

Oct 23, 2020
Minho Ryu, Kichun Lee

A pre-trained language model, BERT, has brought significant performance improvements across a range of natural language processing tasks. Since the model is trained on a large corpus of diverse topics, it shows robust performance for domain shift problems in which data distributions at training (source data) and testing (target data) differ while sharing similarities. Despite its great improvements compared to previous models, it still suffers from performance degradation due to domain shifts. To mitigate such problems, we propose a simple but effective unsupervised domain adaptation method, adversarial adaptation with distillation (AAD), which combines the adversarial discriminative domain adaptation (ADDA) framework with knowledge distillation. We evaluate our approach in the task of cross-domain sentiment classification on 30 domain pairs, advancing the state-of-the-art performance for unsupervised domain adaptation in text sentiment classification.


  Access Paper or Ask Questions

Generalized Conditioned Dialogue Generation Based on Pre-trained Language Model

Oct 21, 2020
Yan Zeng, Jian-Yun Nie

We investigate the general problem of conditioned dialogue, in which a condition label is used as input to designate the type of the target response such as a persona. A major challenge for conditioned dialogue generation is the lack of substantial dialogue data labeled with conditions. Thus, we propose to complement the labeled dialogue data with labeled non-dialogue text data, and fine-tune BERT based on them. Our fine-tuning approach utilizes BERT for both encoder and decoder via different input representations and self-attention masks in order to distinguish the source and target side. On the target (generation) side, we use a new attention routing mechanism to choose between generating a generic word or condition-related word at each position. Our model is instantiated to persona- and topic-related dialogue. Experimental results in both cases show that our approach can produce significantly better responses than the state-of-the-art baselines.

* 9 pages, 2 figures 

  Access Paper or Ask Questions

SupMMD: A Sentence Importance Model for Extractive Summarization using Maximum Mean Discrepancy

Oct 06, 2020
Umanga Bista, Alexander Patrick Mathews, Aditya Krishna Menon, Lexing Xie

Most work on multi-document summarization has focused on generic summarization of information present in each individual document set. However, the under-explored setting of update summarization, where the goal is to identify the new information present in each set, is of equal practical interest (e.g., presenting readers with updates on an evolving news topic). In this work, we present SupMMD, a novel technique for generic and update summarization based on the maximum mean discrepancy from kernel two-sample testing. SupMMD combines both supervised learning for salience and unsupervised learning for coverage and diversity. Further, we adapt multiple kernel learning to make use of similarity across multiple information sources (e.g., text features and knowledge based concepts). We show the efficacy of SupMMD in both generic and update summarization tasks by meeting or exceeding the current state-of-the-art on the DUC-2004 and TAC-2009 datasets.

* EMNLP 2020 
* 15 pages 

  Access Paper or Ask Questions

Evaluation of an indoor localization system for a mobile robot

Sep 24, 2020
Victor J. Exposito Jimenez, Christian Schwarzl, Helmut Martin

Although indoor localization has been a wide researched topic, obtained results may not fit the requirements that some domains need. Most approaches are not able to precisely localize a fast moving object even with a complex installation, which makes their implementation in the automated driving domain complicated. In this publication, common technologies were analyzed and a commercial product, called Marvelmind Indoor GPS, was chosen for our use case in which both ultrasound and radio frequency communications are used. The evaluation is given in a first moment on small indoor scenarios with static and moving objects. Further tests were done on wider areas, where the system is integrated within our Robotics Operating System (ROS)-based self-developed 'Smart PhysIcal Demonstration and evaluation Robot (SPIDER)' and the results of these outdoor tests are compared with the obtained localization by the installed GPS on the robot. Finally, the next steps to improve the results in further developments are discussed.

* 2019 IEEE International Conference on Connected Vehicles and Expo (ICCVE) 

  Access Paper or Ask Questions

Improving Joint Layer RNN based Keyphrase Extraction by Using Syntactical Features

Sep 15, 2020
Miftahul Mahfuzh, Sidik Soleman, Ayu Purwarianti

Keyphrase extraction as a task to identify important words or phrases from a text, is a crucial process to identify main topics when analyzing texts from a social media platform. In our study, we focus on text written in Indonesia language taken from Twitter. Different from the original joint layer recurrent neural network (JRNN) with output of one sequence of keywords and using only word embedding, here we propose to modify the input layer of JRNN to extract more than one sequence of keywords by additional information of syntactical features, namely part of speech, named entity types, and dependency structures. Since JRNN in general requires a large amount of data as the training examples and creating those examples is expensive, we used a data augmentation method to increase the number of training examples. Our experiment had shown that our method outperformed the baseline methods. Our method achieved .9597 in accuracy and .7691 in F1.

* 2019 International Conference of Advanced Informatics: Concepts, Theory and Applications (ICAICTA) 
* 6 pages 

  Access Paper or Ask Questions

Can We Spot the "Fake News" Before It Was Even Written?

Aug 10, 2020
Preslav Nakov

Given the recent proliferation of disinformation online, there has been also growing research interest in automatically debunking rumors, false claims, and "fake news." A number of fact-checking initiatives have been launched so far, both manual and automatic, but the whole enterprise remains in a state of crisis: by the time a claim is finally fact-checked, it could have reached millions of users, and the harm caused could hardly be undone. An arguably more promising direction is to focus on fact-checking entire news outlets, which can be done in advance. Then, we could fact-check the news before it was even written: by checking how trustworthy the outlets that published it is. We describe how we do this in the Tanbih news aggregator, which makes readers aware of what they are reading. In particular, we develop media profiles that show the general factuality of reporting, the degree of propagandistic content, hyper-partisanship, leading political ideology, general frame of reporting, and stance with respect to various claims and topics.

* Fake News, Disinformation, Media Bias, Propaganda, Infodemic, COVID-19 

  Access Paper or Ask Questions

<<
304
305
306
307
308
309
310
311
312
313
314
315
316
>>