Paper Group NANR 176
Robust Histopathology Image Analysis: To Label or to Synthesize?. End-To-End Interpretable Neural Motion Planner. Learning Binary Code for Personalized Fashion Recommendation. Goal-Oriented End-to-End Conversational Models with Profile Features in a Real-World Setting. Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manua …
Robust Histopathology Image Analysis: To Label or to Synthesize?
| Title | Robust Histopathology Image Analysis: To Label or to Synthesize? |
| Authors | Le Hou, Ayush Agarwal, Dimitris Samaras, Tahsin M. Kurc, Rajarsi R. Gupta, Joel H. Saltz |
| Abstract | Detection, segmentation and classification of nuclei are fundamental analysis operations in digital pathology. Existing state-of-the-art approaches demand extensive amount of supervised training data from pathologists and may still perform poorly in images from unseen tissue types. We propose an unsupervised approach for histopathology image segmentation that synthesizes heterogeneous sets of training image patches, of every tissue type. Although our synthetic patches are not always of high quality, we harness the motley crew of generated samples through a generally applicable importance sampling method. This proposed approach, for the first time, re-weighs the training loss over synthetic data so that the ideal (unbiased) generalization loss over the true data distribution is minimized. This enables us to use a random polygon generator to synthesize approximate cellular structures (i.e., nuclear masks) for which no real examples are given in many tissue types, and hence, GAN-based methods are not suited. In addition, we propose a hybrid synthesis pipeline that utilizes textures in real histopathology patches and GAN models, to tackle heterogeneity in tissue textures. Compared with existing state-of-the-art supervised models, our approach generalizes significantly better on cancer types without training data. Even in cancer types with training data, our approach achieves the same performance without supervision cost. We release code and segmentation results on over 5000 Whole Slide Images (WSI) in The Cancer Genome Atlas (TCGA) repository, a dataset that would be orders of magnitude larger than what is available today. |
| Tasks | Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Hou_Robust_Histopathology_Image_Analysis_To_Label_or_to_Synthesize_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Hou_Robust_Histopathology_Image_Analysis_To_Label_or_to_Synthesize_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/robust-histopathology-image-analysis-to-label |
| Repo | |
| Framework | |
End-To-End Interpretable Neural Motion Planner
| Title | End-To-End Interpretable Neural Motion Planner |
| Authors | Wenyuan Zeng, Wenjie Luo, Simon Suo, Abbas Sadat, Bin Yang, Sergio Casas, Raquel Urtasun |
| Abstract | In this paper, we propose a neural motion planner for learning to drive autonomously in complex urban scenarios that include traffic-light handling, yielding, and interactions with multiple road-users. Towards this goal, we design a holistic model that takes as input raw LIDAR data and a HD map and produces interpretable intermediate representations in the form of 3D detections and their future trajectories, as well as a cost volume defining the goodness of each position that the self-driving car can take within the planning horizon. We then sample a set of diverse physically possible trajectories and choose the one with the minimum learned cost. Importantly, our cost volume is able to naturally capture multi-modality. We demonstrate the effectiveness of our approach in real-world driving data captured in several cities in North America. Our experiments show that the learned cost volume can generate safer planning than all the baselines. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zeng_End-To-End_Interpretable_Neural_Motion_Planner_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zeng_End-To-End_Interpretable_Neural_Motion_Planner_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-interpretable-neural-motion |
| Repo | |
| Framework | |
Learning Binary Code for Personalized Fashion Recommendation
| Title | Learning Binary Code for Personalized Fashion Recommendation |
| Authors | Zhi Lu, Yang Hu, Yunchao Jiang, Yan Chen, Bing Zeng |
| Abstract | With the rapid growth of fashion-focused social networks and online shopping, intelligent fashion recommendation is now in great needs. Recommending fashion outfits, each of which is composed of multiple interacted clothing and accessories, is relatively new to the field. The problem becomes even more interesting and challenging when considering users’ personalized fashion style. Another challenge in a large-scale fashion outfit recommendation system is the efficiency issue of item/outfit search and storage. In this paper, we propose to learn binary code for efficient personalized fashion outfits recommendation. Our system consists of three components, a feature network for content extraction, a set of type-dependent hashing modules to learn binary codes, and a matching block that conducts pairwise matching. The whole framework is trained in an end-to-end manner. We collect outfit data together with user label information from a fashion-focused social website for the personalized recommendation task. Extensive experiments on our datasets show that the proposed framework outperforms the state-of-the-art methods significantly even with a simple backbone. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Lu_Learning_Binary_Code_for_Personalized_Fashion_Recommendation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Lu_Learning_Binary_Code_for_Personalized_Fashion_Recommendation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-binary-code-for-personalized-fashion |
| Repo | |
| Framework | |
Goal-Oriented End-to-End Conversational Models with Profile Features in a Real-World Setting
| Title | Goal-Oriented End-to-End Conversational Models with Profile Features in a Real-World Setting |
| Authors | Yichao Lu, Manisha Srivastava, Jared Kramer, Heba Elfardy, Andrea Kahn, Song Wang, Vikas Bhardwaj |
| Abstract | End-to-end neural models for goal-oriented conversational systems have become an increasingly active area of research, though results in real-world settings are few. We present real-world results for two issue types in the customer service domain. We train models on historical chat transcripts and test on live contacts using a human-in-the-loop research platform. Additionally, we incorporate customer profile features to assess their impact on model performance. We experiment with two approaches for response generation: (1) sequence-to-sequence generation and (2) template ranking. To test our models, a customer service agent handles live contacts and at each turn we present the top four model responses and allow the agent to select (and optionally edit) one of the suggestions or to type their own. We present results for turn acceptance rate, response coverage, and edit rate based on approximately 600 contacts, as well as qualitative analysis on patterns of turn rejection and edit behavior. Top-4 turn acceptance rate across all models ranges from 63{%}-80{%}. Our results suggest that these models are promising for an agent-support application. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-2007/ |
| https://www.aclweb.org/anthology/N19-2007 | |
| PWC | https://paperswithcode.com/paper/goal-oriented-end-to-end-conversational |
| Repo | |
| Framework | |
Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features
| Title | Detecting Customer Complaint Escalation with Recurrent Neural Networks and Manually-Engineered Features |
| Authors | Wei Yang, Luchen Tan, Chunwei Lu, Anqi Cui, Han Li, Xi Chen, Kun Xiong, Muzi Wang, Ming Li, Jian Pei, Jimmy Lin |
| Abstract | Consumers dissatisfied with the normal dispute resolution process provided by an e-commerce company{'}s customer service agents have the option of escalating their complaints by filing grievances with a government authority. This paper tackles the challenge of monitoring ongoing text chat dialogues to identify cases where the customer expresses such an intent, providing triage and prioritization for a separate pool of specialized agents specially trained to handle more complex situations. We describe a hybrid model that tackles this challenge by integrating recurrent neural networks with manually-engineered features. Experiments show that both components are complementary and contribute to overall recall, outperforming competitive baselines. A trial online deployment of our model demonstrates its business value in improving customer service. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-2008/ |
| https://www.aclweb.org/anthology/N19-2008 | |
| PWC | https://paperswithcode.com/paper/detecting-customer-complaint-escalation-with |
| Repo | |
| Framework | |
Unconstrained Motion Deblurring for Dual-Lens Cameras
| Title | Unconstrained Motion Deblurring for Dual-Lens Cameras |
| Authors | M. R. Mahesh Mohan, Sharath Girish, A. N. Rajagopalan |
| Abstract | Recently, there has been a renewed interest in leveraging multiple cameras, but under unconstrained settings. They have been quite successfully deployed in smartphones, which have become de facto choice for many photographic applications. However, akin to normal cameras, the functionality of multi-camera systems can be marred by motion blur which is a ubiquitous phenomenon in hand-held cameras. Despite the far-reaching potential of unconstrained camera arrays, there is not a single deblurring method for such systems. In this paper, we propose a generalized blur model that elegantly explains the intrinsically coupled image formation model for dual-lens set-up, which are by far most predominant in smartphones. While image aesthetics is the main objective in normal camera deblurring, any method conceived for our problem is additionally tasked with ascertaining consistent scene-depth in the deblurred images. We reveal an intriguing challenge that stems from an inherent ambiguity unique to this problem which naturally disrupts this coherence. We address this issue by devising a judicious prior, and based on our model and prior propose a practical blind deblurring method for dual-lens cameras, that achieves state-of-the-art performance. |
| Tasks | Deblurring |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Mohan_Unconstrained_Motion_Deblurring_for_Dual-Lens_Cameras_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Mohan_Unconstrained_Motion_Deblurring_for_Dual-Lens_Cameras_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/unconstrained-motion-deblurring-for-dual-lens |
| Repo | |
| Framework | |
Context-Aware Spatio-Recurrent Curvilinear Structure Segmentation
| Title | Context-Aware Spatio-Recurrent Curvilinear Structure Segmentation |
| Authors | Feigege Wang, Yue Gu, Wenxi Liu, Yuanlong Yu, Shengfeng He, Jia Pan |
| Abstract | Curvilinear structures are frequently observed in various images in different forms, such as blood vessels or neuronal boundaries in biomedical images. In this paper, we propose a novel curvilinear structure segmentation approach using context-aware spatio-recurrent networks. Instead of directly segmenting the whole image or densely segmenting fixed-sized local patches, our method recurrently samples patches with varied scales from the target image with learned policy and processes them locally, which is similar to the behavior of changing retinal fixations in the human visual system and it is beneficial for capturing the multi-scale or hierarchical modality of the complex curvilinear structures. In specific, the policy of choosing local patches is attentively learned based on the contextual information of the image and the historical sampling experience. In this way, with more patches sampled and refined, the segmentation of the whole image can be progressively improved. To validate our approach, comparison experiments on different types of image data are conducted and the sampling procedures for exemplar images are illustrated. We demonstrate that our method achieves the state-of-the-art performance in public datasets. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Context-Aware_Spatio-Recurrent_Curvilinear_Structure_Segmentation_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Context-Aware_Spatio-Recurrent_Curvilinear_Structure_Segmentation_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/context-aware-spatio-recurrent-curvilinear |
| Repo | |
| Framework | |
Utilizing Pre-Trained Word Embeddings to Learn Classification Lexicons with Little Supervision
| Title | Utilizing Pre-Trained Word Embeddings to Learn Classification Lexicons with Little Supervision |
| Authors | Frederick Blumenthal, Ferdin Graf, |
| Abstract | |
| Tasks | Word Embeddings |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6402/ |
| https://www.aclweb.org/anthology/W19-6402 | |
| PWC | https://paperswithcode.com/paper/utilizing-pre-trained-word-embeddings-to |
| Repo | |
| Framework | |
Detecting context abusiveness using hierarchical deep learning
| Title | Detecting context abusiveness using hierarchical deep learning |
| Authors | Ju-Hyoung Lee, Jun-U Park, Jeong-Won Cha, Yo-Sub Han |
| Abstract | Abusive text is a serious problem in social media and causes many issues among users as the number of users and the content volume increase. There are several attempts for detecting or preventing abusive text effectively. One simple yet effective approach is to use an abusive lexicon and determine the existence of an abusive word in text. This approach works well even when an abusive word is obfuscated. On the other hand, it is still a challenging problem to determine abusiveness in a text having no explicit abusive words. Especially, it is hard to identify sarcasm or offensiveness in context without any abusive words. We tackle this problem using an ensemble deep learning model. Our model consists of two parts of extracting local features and global features, which are crucial for identifying implicit abusiveness in context level. We evaluate our model using three benchmark data. Our model outperforms all the previous models for detecting abusiveness in a text data without abusive words. Furthermore, we combine our model and an abusive lexicon method. The experimental results show that our model has at least 4{%} better performance compared with the previous approaches for identifying text abusiveness in case of with/without abusive words. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5002/ |
| https://www.aclweb.org/anthology/D19-5002 | |
| PWC | https://paperswithcode.com/paper/detecting-context-abusiveness-using |
| Repo | |
| Framework | |
Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network
| Title | Racial Faces in the Wild: Reducing Racial Bias by Information Maximization Adaptation Network |
| Authors | Mei Wang, Weihong Deng, Jiani Hu, Xunqiang Tao, Yaohai Huang |
| Abstract | Racial bias is an important issue in biometric, but has not been thoroughly studied in deep face recognition. In this paper, we first contribute a dedicated dataset called Racial Faces in-the-Wild (RFW) database, on which we firmly validated the racial bias of four commercial APIs and four state-of-the-art (SOTA) algorithms. Then, we further present the solution using deep unsupervised domain adaptation and propose a deep information maximization adaptation network (IMAN) to alleviate this bias by using Caucasian as source domain and other races as target domains. This unsupervised method simultaneously aligns global distribution to decrease race gap at domain-level, and learns the discriminative target representations at cluster level. A novel mutual information loss is proposed to further enhance the discriminative ability of network output without label information. Extensive experiments on RFW, GBU, and IJB-A databases show that IMAN successfully learns features that generalize well across different races and across different databases. |
| Tasks | Domain Adaptation, Face Recognition, Unsupervised Domain Adaptation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Wang_Racial_Faces_in_the_Wild_Reducing_Racial_Bias_by_Information_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Wang_Racial_Faces_in_the_Wild_Reducing_Racial_Bias_by_Information_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/racial-faces-in-the-wild-reducing-racial-bias-1 |
| Repo | |
| Framework | |
Analysis of Feature Visibility in Non-Line-Of-Sight Measurements
| Title | Analysis of Feature Visibility in Non-Line-Of-Sight Measurements |
| Authors | Xiaochun Liu, Sebastian Bauer, Andreas Velten |
| Abstract | We formulate an equation describing a general Non-line-of-sight (NLOS) imaging measurement and analyze the properties of the measurement in the Fourier domain regarding the spatial frequencies of the scene it encodes. We conclude that for a relay wall with finite size, certain scene configurations and features are not detectable in an NLOS measurement. We then provide experimental examples of invisible scene features and their reconstructions, as well as a set of example scenes that lead to an ill-posed NLOS imaging problem. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Liu_Analysis_of_Feature_Visibility_in_Non-Line-Of-Sight_Measurements_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Liu_Analysis_of_Feature_Visibility_in_Non-Line-Of-Sight_Measurements_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/analysis-of-feature-visibility-in-non-line-of |
| Repo | |
| Framework | |
Persistence pays off: Paying Attention to What the LSTM Gating Mechanism Persists
| Title | Persistence pays off: Paying Attention to What the LSTM Gating Mechanism Persists |
| Authors | Giancarlo Salton, John Kelleher |
| Abstract | Recurrent Neural Network Language Models composed of LSTM units, especially those augmented with an external memory, have achieved state-of-the-art results in Language Modeling. However, these models still struggle to process long sequences which are more likely to contain long-distance dependencies because of information fading. In this paper we demonstrate an effective mechanism for retrieving information in a memory augmented LSTM LM based on attending to information in memory in proportion to the number of timesteps the LSTM gating mechanism persisted the information. |
| Tasks | Language Modelling |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1121/ |
| https://www.aclweb.org/anthology/R19-1121 | |
| PWC | https://paperswithcode.com/paper/persistence-pays-off-paying-attention-to-what-1 |
| Repo | |
| Framework | |
Y’all should read this! Identifying Plurality in Second-Person Personal Pronouns in English Texts
| Title | Y’all should read this! Identifying Plurality in Second-Person Personal Pronouns in English Texts |
| Authors | Gabriel Stanovsky, Ronen Tamari |
| Abstract | Distinguishing between singular and plural {}you{''} in English is a challenging task which has potential for downstream applications, such as machine translation or coreference resolution. While formal written English does not distinguish between these cases, other languages (such as Spanish), as well as other dialects of English (via phrases such as {}y{'}all{''}), do make this distinction. We make use of this to obtain distantly-supervised labels for the task on a large-scale in two domains. Following, we train a model to distinguish between the single/plural {`}you{'}, finding that although in-domain training achieves reasonable accuracy ({\mbox{$\geq$}} 77{%}), there is still a lot of room for improvement, especially in the domain-transfer scenario, which proves extremely challenging. Our code and data are publicly available. | |
| Tasks | Coreference Resolution, Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5549/ |
| https://www.aclweb.org/anthology/D19-5549 | |
| PWC | https://paperswithcode.com/paper/yall-should-read-this-identifying-plurality-1 |
| Repo | |
| Framework | |
CRAFT Shared Tasks 2019 Overview — Integrated Structure, Semantics, and Coreference
| Title | CRAFT Shared Tasks 2019 Overview — Integrated Structure, Semantics, and Coreference |
| Authors | William Baumgartner, Michael Bada, Sampo Pyysalo, Manuel R. Ciosici, Negacy Hailu, Harrison Pielke-Lombardo, Michael Regan, Lawrence Hunter |
| Abstract | As part of the BioNLP Open Shared Tasks 2019, the CRAFT Shared Tasks 2019 provides a platform to gauge the state of the art for three fundamental language processing tasks {—} dependency parse construction, coreference resolution, and ontology concept identification {—} over full-text biomedical articles. The structural annotation task requires the automatic generation of dependency parses for each sentence of an article given only the article text. The coreference resolution task focuses on linking coreferring base noun phrase mentions into chains using the symmetrical and transitive identity relation. The ontology concept annotation task involves the identification of concept mentions within text using the classes of ten distinct ontologies in the biomedical domain, both unmodified and augmented with extension classes. This paper provides an overview of each task, including descriptions of the data provided to participants and the evaluation metrics used, and discusses participant results relative to baseline performances for each of the three tasks. |
| Tasks | Coreference Resolution, Dependency Parsing, Medical Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5725/ |
| https://www.aclweb.org/anthology/D19-5725 | |
| PWC | https://paperswithcode.com/paper/craft-shared-tasks-2019-overview-integrated |
| Repo | |
| Framework | |
Audio De-identification - a New Entity Recognition Task
| Title | Audio De-identification - a New Entity Recognition Task |
| Authors | Ido Cohn, Itay Laish, Genady Beryozkin, Gang Li, Izhak Shafran, Idan Szpektor, Tzvika Hartman, Avinatan Hassidim, Yossi Matias |
| Abstract | Named Entity Recognition (NER) has been mostly studied in the context of written text. Specifically, NER is an important step in de-identification (de-ID) of medical records, many of which are recorded conversations between a patient and a doctor. In such recordings, audio spans with personal information should be redacted, similar to the redaction of sensitive character spans in de-ID for written text. The application of NER in the context of audio de-identification has yet to be fully investigated. To this end, we define the task of audio de-ID, in which audio spans with entity mentions should be detected. We then present our pipeline for this task, which involves Automatic Speech Recognition (ASR), NER on the transcript text, and text-to-audio alignment. Finally, we introduce a novel metric for audio de-ID and a new evaluation benchmark consisting of a large labeled segment of the Switchboard and Fisher audio datasets and detail our pipeline{'}s results on it. |
| Tasks | Named Entity Recognition, Speech Recognition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-2025/ |
| https://www.aclweb.org/anthology/N19-2025 | |
| PWC | https://paperswithcode.com/paper/audio-de-identification-a-new-entity-1 |
| Repo | |
| Framework | |
