Paper Group ANR 671
An Universal Image Attractiveness Ranking Framework. Incorporating Scalability in Unsupervised Spatio-Temporal Feature Learning. Labelling as an unsupervised learning problem. Deep neural network marketplace recommenders in online experiments. Learning to Anonymize Faces for Privacy Preserving Action Detection. Automatic construction of Chinese her …
An Universal Image Attractiveness Ranking Framework
| Title | An Universal Image Attractiveness Ranking Framework |
| Authors | Ning Ma, Alexey Volkov, Aleksandr Livshits, Pawel Pietrusinski, Houdong Hu, Mark Bolin |
| Abstract | We propose a new framework to rank image attractiveness using a novel pairwise deep network trained with a large set of side-by-side multi-labeled image pairs from a web image index. The judges only provide relative ranking between two images without the need to directly assign an absolute score, or rate any predefined image attribute, thus making the rating more intuitive and accurate. We investigate a deep attractiveness rank net (DARN), a combination of deep convolutional neural network and rank net, to directly learn an attractiveness score mean and variance for each image and the underlying criteria the judges use to label each pair. The extension of this model (DARN-V2) is able to adapt to individual judge’s personal preference. We also show the attractiveness of search results are significantly improved by using this attractiveness information in a real commercial search engine. We evaluate our model against other state-of-the-art models on our side-by-side web test data and another public aesthetic data set. With much less judgments (1M vs 50M), our model outperforms on side-by-side labeled data, and is comparable on data labeled by absolute score. |
| Tasks | |
| Published | 2018-04-12 |
| URL | http://arxiv.org/abs/1805.00309v3 |
| http://arxiv.org/pdf/1805.00309v3.pdf | |
| PWC | https://paperswithcode.com/paper/an-universal-image-attractiveness-ranking |
| Repo | |
| Framework | |
Incorporating Scalability in Unsupervised Spatio-Temporal Feature Learning
| Title | Incorporating Scalability in Unsupervised Spatio-Temporal Feature Learning |
| Authors | Sujoy Paul, Sourya Roy, Amit K. Roy-Chowdhury |
| Abstract | Deep neural networks are efficient learning machines which leverage upon a large amount of manually labeled data for learning discriminative features. However, acquiring substantial amount of supervised data, especially for videos can be a tedious job across various computer vision tasks. This necessitates learning of visual features from videos in an unsupervised setting. In this paper, we propose a computationally simple, yet effective, framework to learn spatio-temporal feature embedding from unlabeled videos. We train a Convolutional 3D Siamese network using positive and negative pairs mined from videos under certain probabilistic assumptions. Experimental results on three datasets demonstrate that our proposed framework is able to learn weights which can be used for same as well as cross dataset and tasks. |
| Tasks | |
| Published | 2018-08-06 |
| URL | http://arxiv.org/abs/1808.01727v2 |
| http://arxiv.org/pdf/1808.01727v2.pdf | |
| PWC | https://paperswithcode.com/paper/incorporating-scalability-in-unsupervised |
| Repo | |
| Framework | |
Labelling as an unsupervised learning problem
| Title | Labelling as an unsupervised learning problem |
| Authors | Terry Lyons, Imanol Perez Arribas |
| Abstract | Unravelling hidden patterns in datasets is a classical problem with many potential applications. In this paper, we present a challenge whose objective is to discover nonlinear relationships in noisy cloud of points. If a set of point satisfies a nonlinear relationship that is unlikely to be due to randomness, we will label the set with this relationship. Since points can satisfy one, many or no such nonlinear relationships, cloud of points will typically have one, multiple or no labels at all. This introduces the labelling problem that will be studied in this paper. The objective of this paper is to develop a framework for the labelling problem. We introduce a precise notion of a label, and we propose an algorithm to discover such labels in a given dataset, which is then tested in synthetic datasets. We also analyse, using tools from random matrix theory, the problem of discovering false labels in the dataset. |
| Tasks | |
| Published | 2018-05-10 |
| URL | http://arxiv.org/abs/1805.03911v2 |
| http://arxiv.org/pdf/1805.03911v2.pdf | |
| PWC | https://paperswithcode.com/paper/labelling-as-an-unsupervised-learning-problem |
| Repo | |
| Framework | |
Deep neural network marketplace recommenders in online experiments
| Title | Deep neural network marketplace recommenders in online experiments |
| Authors | Simen Eide, Ning Zhou |
| Abstract | Recommendations are broadly used in marketplaces to match users with items relevant to their interests and needs. To understand user intent and tailor recommendations to their needs, we use deep learning to explore various heterogeneous data available in marketplaces. This paper focuses on the challenge of measuring recommender performance and summarizes the online experiment results with several promising types of deep neural network recommenders - hybrid item representation models combining features from user engagement and content, sequence-based models, and multi-armed bandit models that optimize user engagement by re-ranking proposals from multiple submodels. The recommenders are currently running in production at the leading Norwegian marketplace FINN.no and serves over one million visitors everyday. |
| Tasks | |
| Published | 2018-09-06 |
| URL | http://arxiv.org/abs/1809.02130v1 |
| http://arxiv.org/pdf/1809.02130v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-neural-network-marketplace-recommenders |
| Repo | |
| Framework | |
Learning to Anonymize Faces for Privacy Preserving Action Detection
| Title | Learning to Anonymize Faces for Privacy Preserving Action Detection |
| Authors | Zhongzheng Ren, Yong Jae Lee, Michael S. Ryoo |
| Abstract | There is an increasing concern in computer vision devices invading users’ privacy by recording unwanted videos. On the one hand, we want the camera systems to recognize important events and assist human daily lives by understanding its videos, but on the other hand we want to ensure that they do not intrude people’s privacy. In this paper, we propose a new principled approach for learning a video \emph{face anonymizer}. We use an adversarial training setting in which two competing systems fight: (1) a video anonymizer that modifies the original video to remove privacy-sensitive information while still trying to maximize spatial action detection performance, and (2) a discriminator that tries to extract privacy-sensitive information from the anonymized videos. The end result is a video anonymizer that performs pixel-level modifications to anonymize each person’s face, with minimal effect on action detection performance. We experimentally confirm the benefits of our approach compared to conventional hand-crafted anonymization methods including masking, blurring, and noise adding. Code, demo, and more results can be found on our project page https://jason718.github.io/project/privacy/main.html. |
| Tasks | Action Detection |
| Published | 2018-03-30 |
| URL | http://arxiv.org/abs/1803.11556v2 |
| http://arxiv.org/pdf/1803.11556v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-anonymize-faces-for-privacy |
| Repo | |
| Framework | |
Automatic construction of Chinese herbal prescription from tongue image via CNNs and auxiliary latent therapy topics
| Title | Automatic construction of Chinese herbal prescription from tongue image via CNNs and auxiliary latent therapy topics |
| Authors | Yang Hu, Guihua Wen, Huiqiang Liao, Changjun Wang, Dan Dai, Zhiwen Yu |
| Abstract | The tongue image provides important physical information of humans. It is of great importance for diagnoses and treatments in clinical medicine. Herbal prescriptions are simple, noninvasive and have low side effects. Thus, they are widely applied in China. Studies on the automatic construction technology of herbal prescriptions based on tongue images have great significance for deep learning to explore the relevance of tongue images for herbal prescriptions, it can be applied to healthcare services in mobile medical systems. In order to adapt to the tongue image in a variety of photographic environments and construct herbal prescriptions, a neural network framework for prescription construction is designed. It includes single/double convolution channels and fully connected layers. Furthermore, it proposes the auxiliary therapy topic loss mechanism to model the therapy of Chinese doctors and alleviate the interference of sparse output labels on the diversity of results. The experiment use the real world tongue images and the corresponding prescriptions and the results can generate prescriptions that are close to the real samples, which verifies the feasibility of the proposed method for the automatic construction of herbal prescriptions from tongue images. Also, it provides a reference for automatic herbal prescription construction from more physical information. |
| Tasks | |
| Published | 2018-01-23 |
| URL | https://arxiv.org/abs/1802.02203v4 |
| https://arxiv.org/pdf/1802.02203v4.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-construction-of-chinese-herbal |
| Repo | |
| Framework | |
Anonymizing k-Facial Attributes via Adversarial Perturbations
| Title | Anonymizing k-Facial Attributes via Adversarial Perturbations |
| Authors | Saheb Chhabra, Richa Singh, Mayank Vatsa, Gaurav Gupta |
| Abstract | A face image not only provides details about the identity of a subject but also reveals several attributes such as gender, race, sexual orientation, and age. Advancements in machine learning algorithms and popularity of sharing images on the World Wide Web, including social media websites, have increased the scope of data analytics and information profiling from photo collections. This poses a serious privacy threat for individuals who do not want to be profiled. This research presents a novel algorithm for anonymizing selective attributes which an individual does not want to share without affecting the visual quality of images. Using the proposed algorithm, a user can select single or multiple attributes to be surpassed while preserving identity information and visual content. The proposed adversarial perturbation based algorithm embeds imperceptible noise in an image such that attribute prediction algorithm for the selected attribute yields incorrect classification result, thereby preserving the information according to user’s choice. Experiments on three popular databases i.e. MUCT, LFWcrop, and CelebA show that the proposed algorithm not only anonymizes k-attributes, but also preserves image quality and identity information. |
| Tasks | |
| Published | 2018-05-23 |
| URL | http://arxiv.org/abs/1805.09380v2 |
| http://arxiv.org/pdf/1805.09380v2.pdf | |
| PWC | https://paperswithcode.com/paper/anonymizing-k-facial-attributes-via |
| Repo | |
| Framework | |
Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network
| Title | Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) Network |
| Authors | Alex Sherstinsky |
| Abstract | Because of their effectiveness in broad practical applications, LSTM networks have received a wealth of coverage in scientific journals, technical blogs, and implementation guides. However, in most articles, the inference formulas for the LSTM network and its parent, RNN, are stated axiomatically, while the training formulas are omitted altogether. In addition, the technique of “unrolling” an RNN is routinely presented without justification throughout the literature. The goal of this paper is to explain the essential RNN and LSTM fundamentals in a single document. Drawing from concepts in signal processing, we formally derive the canonical RNN formulation from differential equations. We then propose and prove a precise statement, which yields the RNN unrolling technique. We also review the difficulties with training the standard RNN and address them by transforming the RNN into the “Vanilla LSTM” network through a series of logical arguments. We provide all equations pertaining to the LSTM system together with detailed descriptions of its constituent entities. Albeit unconventional, our choice of notation and the method for presenting the LSTM system emphasizes ease of understanding. As part of the analysis, we identify new opportunities to enrich the LSTM system and incorporate these extensions into the Vanilla LSTM network, producing the most general LSTM variant to date. The target reader has already been exposed to RNNs and LSTM networks through numerous available resources and is open to an alternative pedagogical approach. A Machine Learning practitioner seeking guidance for implementing our new augmented LSTM model in software for experimentation and research will find the insights and derivations in this tutorial valuable as well. |
| Tasks | |
| Published | 2018-08-09 |
| URL | https://arxiv.org/abs/1808.03314v6 |
| https://arxiv.org/pdf/1808.03314v6.pdf | |
| PWC | https://paperswithcode.com/paper/fundamentals-of-recurrent-neural-network-rnn |
| Repo | |
| Framework | |
Is there Gender bias and stereotype in Portuguese Word Embeddings?
| Title | Is there Gender bias and stereotype in Portuguese Word Embeddings? |
| Authors | Brenda Salenave Santana, Vinicius Woloszyn, Leandro Krug Wives |
| Abstract | In this work, we propose an analysis of the presence of gender bias associated with professions in Portuguese word embeddings. The objective of this work is to study gender implications related to stereotyped professions for women and men in the context of the Portuguese language. |
| Tasks | Word Embeddings |
| Published | 2018-10-10 |
| URL | http://arxiv.org/abs/1810.04528v1 |
| http://arxiv.org/pdf/1810.04528v1.pdf | |
| PWC | https://paperswithcode.com/paper/is-there-gender-bias-and-stereotype-in |
| Repo | |
| Framework | |
Model Learning for Look-ahead Exploration in Continuous Control
| Title | Model Learning for Look-ahead Exploration in Continuous Control |
| Authors | Arpit Agarwal, Katharina Muelling, Katerina Fragkiadaki |
| Abstract | We propose an exploration method that incorporates look-ahead search over basic learnt skills and their dynamics, and use it for reinforcement learning (RL) of manipulation policies . Our skills are multi-goal policies learned in isolation in simpler environments using existing multigoal RL formulations, analogous to options or macroactions. Coarse skill dynamics, i.e., the state transition caused by a (complete) skill execution, are learnt and are unrolled forward during lookahead search. Policy search benefits from temporal abstraction during exploration, though itself operates over low-level primitive actions, and thus the resulting policies does not suffer from suboptimality and inflexibility caused by coarse skill chaining. We show that the proposed exploration strategy results in effective learning of complex manipulation policies faster than current state-of-the-art RL methods, and converges to better policies than methods that use options or parametrized skills as building blocks of the policy itself, as opposed to guiding exploration. We show that the proposed exploration strategy results in effective learning of complex manipulation policies faster than current state-of-the-art RL methods, and converges to better policies than methods that use options or parameterized skills as building blocks of the policy itself, as opposed to guiding exploration. |
| Tasks | Continuous Control |
| Published | 2018-11-20 |
| URL | http://arxiv.org/abs/1811.08086v1 |
| http://arxiv.org/pdf/1811.08086v1.pdf | |
| PWC | https://paperswithcode.com/paper/model-learning-for-look-ahead-exploration-in |
| Repo | |
| Framework | |
SelfKin: Self Adjusted Deep Model For Kinship Verification
| Title | SelfKin: Self Adjusted Deep Model For Kinship Verification |
| Authors | Eran Dahan, Yosi Keller |
| Abstract | One of the unsolved challenges in the field of biometrics and face recognition is Kinship Verification. This problem aims to understand if two people are family-related and how (sisters, brothers, etc.) Solving this problem can give rise to varied tasks and applications. In the area of homeland security (HLS) it is crucial to auto-detect if the person questioned is related to a wanted suspect, In the field of biometrics, kinship-verification can help to discriminate between families by photos and in the field of predicting or fashion it can help to predict an older or younger model of people faces. Lately, and with the advanced deep learning technology, this problem has gained focus from the research community in matters of data and research. In this article, we propose using a Deep Learning approach for solving the Kinship-Verification problem. Further, we offer a novel self-learning deep model, which learns the essential features from different faces. We show that our model wins the Recognize Families In the Wild(RFIW2018,FG2018) challenge and obtains state-of-the-art results. Moreover, we show that our proposed model can reduce the size of the network by half without loss in performance. |
| Tasks | Face Recognition |
| Published | 2018-09-22 |
| URL | http://arxiv.org/abs/1809.08493v1 |
| http://arxiv.org/pdf/1809.08493v1.pdf | |
| PWC | https://paperswithcode.com/paper/selfkin-self-adjusted-deep-model-for-kinship |
| Repo | |
| Framework | |
Autonomous Self-Explanation of Behavior for Interactive Reinforcement Learning Agents
| Title | Autonomous Self-Explanation of Behavior for Interactive Reinforcement Learning Agents |
| Authors | Yosuke Fukuchi, Masahiko Osawa, Hiroshi Yamakawa, Michita Imai |
| Abstract | In cooperation, the workers must know how co-workers behave. However, an agent’s policy, which is embedded in a statistical machine learning model, is hard to understand, and requires much time and knowledge to comprehend. Therefore, it is difficult for people to predict the behavior of machine learning robots, which makes Human Robot Cooperation challenging. In this paper, we propose Instruction-based Behavior Explanation (IBE), a method to explain an autonomous agent’s future behavior. In IBE, an agent can autonomously acquire the expressions to explain its own behavior by reusing the instructions given by a human expert to accelerate the learning of the agent’s policy. IBE also enables a developmental agent, whose policy may change during the cooperation, to explain its own behavior with sufficient time granularity. |
| Tasks | |
| Published | 2018-10-20 |
| URL | http://arxiv.org/abs/1810.08811v1 |
| http://arxiv.org/pdf/1810.08811v1.pdf | |
| PWC | https://paperswithcode.com/paper/autonomous-self-explanation-of-behavior-for |
| Repo | |
| Framework | |
Injecting Relational Structural Representation in Neural Networks for Question Similarity
| Title | Injecting Relational Structural Representation in Neural Networks for Question Similarity |
| Authors | Antonio Uva, Daniele Bonadiman, Alessandro Moschitti |
| Abstract | Effectively using full syntactic parsing information in Neural Networks (NNs) to solve relational tasks, e.g., question similarity, is still an open problem. In this paper, we propose to inject structural representations in NNs by (i) learning an SVM model using Tree Kernels (TKs) on relatively few pairs of questions (few thousands) as gold standard (GS) training data is typically scarce, (ii) predicting labels on a very large corpus of question pairs, and (iii) pre-training NNs on such large corpus. The results on Quora and SemEval question similarity datasets show that NNs trained with our approach can learn more accurate models, especially after fine tuning on GS. |
| Tasks | Question Similarity |
| Published | 2018-06-20 |
| URL | http://arxiv.org/abs/1806.08009v1 |
| http://arxiv.org/pdf/1806.08009v1.pdf | |
| PWC | https://paperswithcode.com/paper/injecting-relational-structural |
| Repo | |
| Framework | |
How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness
| Title | How Do Fairness Definitions Fare? Examining Public Attitudes Towards Algorithmic Definitions of Fairness |
| Authors | Nripsuta Saxena, Karen Huang, Evan DeFilippis, Goran Radanovic, David Parkes, Yang Liu |
| Abstract | What is the best way to define algorithmic fairness? While many definitions of fairness have been proposed in the computer science literature, there is no clear agreement over a particular definition. In this work, we investigate ordinary people’s perceptions of three of these fairness definitions. Across two online experiments, we test which definitions people perceive to be the fairest in the context of loan decisions, and whether fairness perceptions change with the addition of sensitive information (i.e., race of the loan applicants). Overall, one definition (calibrated fairness) tends to be more preferred than the others, and the results also provide support for the principle of affirmative action. |
| Tasks | |
| Published | 2018-11-08 |
| URL | http://arxiv.org/abs/1811.03654v2 |
| http://arxiv.org/pdf/1811.03654v2.pdf | |
| PWC | https://paperswithcode.com/paper/how-do-fairness-definitions-fare-examining |
| Repo | |
| Framework | |
MIST: Multiple Instance Spatial Transformer Network
| Title | MIST: Multiple Instance Spatial Transformer Network |
| Authors | Baptiste Angles, Simon Kornblith, Shahram Izadi, Andrea Tagliasacchi, Kwang Moo Yi |
| Abstract | We propose a deep network that can be trained to tackle image reconstruction and classification problems that involve detection of multiple object instances, without any supervision regarding their whereabouts. The network learns to extract the most significant top-K patches, and feeds these patches to a task-specific network – e.g., auto-encoder or classifier – to solve a domain specific problem. The challenge in training such a network is the non-differentiable top-K selection process. To address this issue, we lift the training optimization problem by treating the result of top-K selection as a slack variable, resulting in a simple, yet effective, multi-stage training. Our method is able to learn to detect recurrent structures in the training dataset by learning to reconstruct images. It can also learn to localize structures when only knowledge on the occurrence of the object is provided, and in doing so it outperforms the state-of-the-art. |
| Tasks | Image Reconstruction |
| Published | 2018-11-26 |
| URL | https://arxiv.org/abs/1811.10725v4 |
| https://arxiv.org/pdf/1811.10725v4.pdf | |
| PWC | https://paperswithcode.com/paper/mist-multiple-instance-spatial-transformer |
| Repo | |
| Framework | |
