Paper Group ANR 1279
Attributes-aided Part Detection and Refinement for Person Re-identification. Flavour Enhanced Food Recommendation. Unsupervised Separation of Dynamics from Pixels. Linking Physicians to Medical Research Results via Knowledge Graph Embeddings and Twitter. Place-specific Background Modeling Using Recursive Autoencoders. Uncertainty-aware Model-based …
Attributes-aided Part Detection and Refinement for Person Re-identification
| Title | Attributes-aided Part Detection and Refinement for Person Re-identification |
| Authors | Shuzhao Li, Huimin Yu, Wei Huang, Jing Zhang |
| Abstract | Person attributes are often exploited as mid-level human semantic information to help promote the performance of person re-identification task. In this paper, unlike most existing methods simply taking attribute learning as a classification problem, we perform it in a different way with the motivation that attributes are related to specific local regions, which refers to the perceptual ability of attributes. We utilize the process of attribute detection to generate corresponding attribute-part detectors, whose invariance to many influences like poses and camera views can be guaranteed. With detected local part regions, our model extracts local features to handle the body part misalignment problem, which is another major challenge for person re-identification. The local descriptors are further refined by fused attribute information to eliminate interferences caused by detection deviation. Extensive experiments on two popular benchmarks with attribute annotations demonstrate the effectiveness of our model and competitive performance compared with state-of-the-art algorithms. |
| Tasks | Person Re-Identification |
| Published | 2019-02-27 |
| URL | http://arxiv.org/abs/1902.10528v1 |
| http://arxiv.org/pdf/1902.10528v1.pdf | |
| PWC | https://paperswithcode.com/paper/attributes-aided-part-detection-and |
| Repo | |
| Framework | |
Flavour Enhanced Food Recommendation
| Title | Flavour Enhanced Food Recommendation |
| Authors | Nitish Nag, Aditya Bharadwaj, Aditya Narendra Rao, Akash Kulhalli, Kushal Samir Mehta, Nishant Bhattacharya, Pratul Ramkumar, Dinkar Sitaram, Ramesh Jain |
| Abstract | We propose a mechanism to use the features of flavour to enhance the quality of food recommendations. An empirical method to determine the flavour of food is incorporated into a recommendation engine based on major gustatory nerves. Such a system has advantages of suggesting food items that the user is more likely to enjoy based upon matching with their flavour profile through use of the taste biological domain knowledge. This preliminary intends to spark more robust mechanisms by which flavour of food is taken into consideration as a major feature set into food recommendation systems. Our long term vision is to integrate this with health factors to recommend healthy and tasty food to users to enhance quality of life. |
| Tasks | Recommendation Systems |
| Published | 2019-04-02 |
| URL | https://arxiv.org/abs/1904.05331v2 |
| https://arxiv.org/pdf/1904.05331v2.pdf | |
| PWC | https://paperswithcode.com/paper/flavour-based-food-recommendation |
| Repo | |
| Framework | |
Unsupervised Separation of Dynamics from Pixels
| Title | Unsupervised Separation of Dynamics from Pixels |
| Authors | Silvia Chiappa, Ulrich Paquet |
| Abstract | We present an approach to learn the dynamics of multiple objects from image sequences in an unsupervised way. We introduce a probabilistic model that first generate noisy positions for each object through a separate linear state-space model, and then renders the positions of all objects in the same image through a highly non-linear process. Such a linear representation of the dynamics enables us to propose an inference method that uses exact and efficient inference tools and that can be deployed to query the model in different ways without retraining. |
| Tasks | |
| Published | 2019-07-20 |
| URL | https://arxiv.org/abs/1907.12906v1 |
| https://arxiv.org/pdf/1907.12906v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-separation-of-dynamics-from |
| Repo | |
| Framework | |
Linking Physicians to Medical Research Results via Knowledge Graph Embeddings and Twitter
| Title | Linking Physicians to Medical Research Results via Knowledge Graph Embeddings and Twitter |
| Authors | Afshin Sadeghi, Jens Lehmann |
| Abstract | Informing professionals about the latest research results in their field is a particularly important task in the field of health care, since any development in this field directly improves the health status of the patients. Meanwhile, social media is an infrastructure that allows public instant sharing of information, thus it has recently become popular in medical applications. In this study, we apply Multi Distance Knowledge Graph Embeddings (MDE) to link physicians and surgeons to the latest medical breakthroughs that are shared as the research results on Twitter. Our study shows that using this method physicians can be informed about the new findings in their field given that they have an account dedicated to their profession. |
| Tasks | Knowledge Graph Embeddings |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1908.02571v3 |
| https://arxiv.org/pdf/1908.02571v3.pdf | |
| PWC | https://paperswithcode.com/paper/linking-physicians-to-medical-research |
| Repo | |
| Framework | |
Place-specific Background Modeling Using Recursive Autoencoders
| Title | Place-specific Background Modeling Using Recursive Autoencoders |
| Authors | Yamaguchi Kousuke, Tanaka Kanji, Sugimoto Takuma, Ide Rino, Takeda Koji |
| Abstract | Image change detection (ICD) to detect changed objects in front of a vehicle with respect to a place-specific background model using an on-board monocular vision system is a fundamental problem in intelligent vehicle (IV). From the perspective of recent large-scale IV applications, it can be impractical in terms of space/time efficiency to train place-specific background models for every possible place. To address these issues, we introduce a new autoencoder (AE) based efficient ICD framework that combines the advantages of AE-based anomaly detection (AD) and AE-based image compression (IC). We propose a method that uses AE reconstruction errors as a single unified measure for training a minimal set of place-specific AEs and maintains detection accuracy. We introduce an efficient incremental recursive AE (rAE) training framework that recursively summarizes a large collection of background images into the AE set. The results of experiments on challenging cross-season ICD tasks validate the efficacy of the proposed approach. |
| Tasks | Anomaly Detection, Image Compression |
| Published | 2019-04-07 |
| URL | http://arxiv.org/abs/1904.03555v1 |
| http://arxiv.org/pdf/1904.03555v1.pdf | |
| PWC | https://paperswithcode.com/paper/place-specific-background-modeling-using |
| Repo | |
| Framework | |
Uncertainty-aware Model-based Policy Optimization
| Title | Uncertainty-aware Model-based Policy Optimization |
| Authors | Tung-Long Vuong, Kenneth Tran |
| Abstract | Model-based reinforcement learning has the potential to be more sample efficient than model-free approaches. However, existing model-based methods are vulnerable to model bias, which leads to poor generalization and asymptotic performance compared to model-free counterparts. In addition, they are typically based on the model predictive control (MPC) framework, which not only is computationally inefficient at decision time but also does not enable policy transfer due to the lack of an explicit policy representation. In this paper, we propose a novel uncertainty-aware model-based policy optimization framework which solves those issues. In this framework, the agent simultaneously learns an uncertainty-aware dynamics model and optimizes the policy according to these learned models. In the optimization step, the policy gradient is computed by automatic differentiation through the models. With respect to sample efficiency alone, our approach shows promising results on challenging continuous control benchmarks with competitive asymptotic performance and significantly lower sample complexity than state-of-the-art baselines. |
| Tasks | Continuous Control |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10717v1 |
| https://arxiv.org/pdf/1906.10717v1.pdf | |
| PWC | https://paperswithcode.com/paper/uncertainty-aware-model-based-policy |
| Repo | |
| Framework | |
Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target
| Title | Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target |
| Authors | J. Fernando Hernandez-Garcia, Richard S. Sutton |
| Abstract | Multi-step methods such as Retrace($\lambda$) and $n$-step $Q$-learning have become a crucial component of modern deep reinforcement learning agents. These methods are often evaluated as a part of bigger architectures and their evaluations rarely include enough samples to draw statistically significant conclusions about their performance. This type of methodology makes it difficult to understand how particular algorithmic details of multi-step methods influence learning. In this paper we combine the $n$-step action-value algorithms Retrace, $Q$-learning, Tree Backup, Sarsa, and $Q(\sigma)$ with an architecture analogous to DQN. We test the performance of all these algorithms in the mountain car environment; this choice of environment allows for faster training times and larger sample sizes. We present statistical analyses on the effects of the off-policy correction, the backup length parameter $n$, and the update frequency of the target network on the performance of these algorithms. Our results show that (1) using off-policy correction can have an adverse effect on the performance of Sarsa and $Q(\sigma)$; (2) increasing the backup length $n$ consistently improved performance across all the different algorithms; and (3) the performance of Sarsa and $Q$-learning was more robust to the effect of the target network update frequency than the performance of Tree Backup, $Q(\sigma)$, and Retrace in this particular task. |
| Tasks | Q-Learning |
| Published | 2019-01-22 |
| URL | http://arxiv.org/abs/1901.07510v2 |
| http://arxiv.org/pdf/1901.07510v2.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-multi-step-deep-reinforcement |
| Repo | |
| Framework | |
Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future
| Title | Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future |
| Authors | Nan Rosemary Ke, Amanpreet Singh, Ahmed Touati, Anirudh Goyal, Yoshua Bengio, Devi Parikh, Dhruv Batra |
| Abstract | In model-based reinforcement learning, the agent interleaves between model learning and planning. These two components are inextricably intertwined. If the model is not able to provide sensible long-term prediction, the executed planner would exploit model flaws, which can yield catastrophic failures. This paper focuses on building a model that reasons about the long-term future and demonstrates how to use this for efficient planning and exploration. To this end, we build a latent-variable autoregressive model by leveraging recent ideas in variational inference. We argue that forcing latent variables to carry future information through an auxiliary task substantially improves long-term predictions. Moreover, by planning in the latent space, the planner’s solution is ensured to be within regions where the model is valid. An exploration strategy can be devised by searching for unlikely trajectories under the model. Our method achieves higher reward faster compared to baselines on a variety of tasks and environments in both the imitation learning and model-based reinforcement learning settings. |
| Tasks | Imitation Learning |
| Published | 2019-03-05 |
| URL | http://arxiv.org/abs/1903.01599v2 |
| http://arxiv.org/pdf/1903.01599v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-dynamics-model-in-reinforcement |
| Repo | |
| Framework | |
Variational f-divergence Minimization
| Title | Variational f-divergence Minimization |
| Authors | Mingtian Zhang, Thomas Bird, Raza Habib, Tianlin Xu, David Barber |
| Abstract | Probabilistic models are often trained by maximum likelihood, which corresponds to minimizing a specific f-divergence between the model and data distribution. In light of recent successes in training Generative Adversarial Networks, alternative non-likelihood training criteria have been proposed. Whilst not necessarily statistically efficient, these alternatives may better match user requirements such as sharp image generation. A general variational method for training probabilistic latent variable models using maximum likelihood is well established; however, how to train latent variable models using other f-divergences is comparatively unknown. We discuss a variational approach that, when combined with the recently introduced Spread Divergence, can be applied to train a large class of latent variable models using any f-divergence. |
| Tasks | Image Generation, Latent Variable Models |
| Published | 2019-07-27 |
| URL | https://arxiv.org/abs/1907.11891v1 |
| https://arxiv.org/pdf/1907.11891v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-f-divergence-minimization |
| Repo | |
| Framework | |
Optimal Analysis of Subset-Selection Based L_p Low Rank Approximation
| Title | Optimal Analysis of Subset-Selection Based L_p Low Rank Approximation |
| Authors | Chen Dan, Hong Wang, Hongyang Zhang, Yuchen Zhou, Pradeep Ravikumar |
| Abstract | We study the low rank approximation problem of any given matrix $A$ over $\mathbb{R}^{n\times m}$ and $\mathbb{C}^{n\times m}$ in entry-wise $\ell_p$ loss, that is, finding a rank-$k$ matrix $X$ such that $\A-X_p$ is minimized. Unlike the traditional $\ell_2$ setting, this particular variant is NP-Hard. We show that the algorithm of column subset selection, which was an algorithmic foundation of many existing algorithms, enjoys approximation ratio $(k+1)^{1/p}$ for $1\le p\le 2$ and $(k+1)^{1-1/p}$ for $p\ge 2$. This improves upon the previous $O(k+1)$ bound for $p\ge 1$ \cite{chierichetti2017algorithms}. We complement our analysis with lower bounds; these bounds match our upper bounds up to constant $1$ when $p\geq 2$. At the core of our techniques is an application of \emph{Riesz-Thorin interpolation theorem} from harmonic analysis, which might be of independent interest to other algorithmic designs and analysis more broadly. As a consequence of our analysis, we provide better approximation guarantees for several other algorithms with various time complexity. For example, to make the algorithm of column subset selection computationally efficient, we analyze a polynomial time bi-criteria algorithm which selects $O(k\log m)$ columns. We show that this algorithm has an approximation ratio of $O((k+1)^{1/p})$ for $1\le p\le 2$ and $O((k+1)^{1-1/p})$ for $p\ge 2$. This improves over the best-known bound with an $O(k+1)$ approximation ratio. Our bi-criteria algorithm also implies an exact-rank method in polynomial time with a slightly larger approximation ratio. |
| Tasks | |
| Published | 2019-10-30 |
| URL | https://arxiv.org/abs/1910.13618v1 |
| https://arxiv.org/pdf/1910.13618v1.pdf | |
| PWC | https://paperswithcode.com/paper/optimal-analysis-of-subset-selection-based |
| Repo | |
| Framework | |
Conditioning by adaptive sampling for robust design
| Title | Conditioning by adaptive sampling for robust design |
| Authors | David H. Brookes, Hahnbeom Park, Jennifer Listgarten |
| Abstract | We present a new method for design problems wherein the goal is to maximize or specify the value of one or more properties of interest. For example, in protein design, one may wish to find the protein sequence that maximizes fluorescence. We assume access to one or more, potentially black box, stochastic “oracle” predictive functions, each of which maps from input (e.g., protein sequences) design space to a distribution over a property of interest (e.g. protein fluorescence). At first glance, this problem can be framed as one of optimizing the oracle(s) with respect to the input. However, many state-of-the-art predictive models, such as neural networks, are known to suffer from pathologies, especially for data far from the training distribution. Thus we need to modulate the optimization of the oracle inputs with prior knowledge about what makes `realistic’ inputs (e.g., proteins that stably fold). Herein, we propose a new method to solve this problem, Conditioning by Adaptive Sampling, which yields state-of-the-art results on a protein fluorescence problem, as compared to other recently published approaches. Formally, our method achieves its success by using model-based adaptive sampling to estimate the conditional distribution of the input sequences given the desired properties. | |
| Tasks | |
| Published | 2019-01-29 |
| URL | https://arxiv.org/abs/1901.10060v8 |
| https://arxiv.org/pdf/1901.10060v8.pdf | |
| PWC | https://paperswithcode.com/paper/conditioning-by-adaptive-sampling-for-robust |
| Repo | |
| Framework | |
Near Neighbor: Who is the Fairest of Them All?
| Title | Near Neighbor: Who is the Fairest of Them All? |
| Authors | Sariel Har-Peled, Sepideh Mahabadi |
| Abstract | $\newcommand{\ball}{\mathbb{B}}\newcommand{\dsQ}{{\mathcal{Q}}}\newcommand{\dsS}{{\mathcal{S}}}$In this work we study a fair variant of the near neighbor problem. Namely, given a set of $n$ points $P$ and a parameter $r$, the goal is to preprocess the points, such that given a query point $q$, any point in the $r$-neighborhood of the query, i.e., $\ball(q,r)$, have the same probability of being reported as the near neighbor. We show that LSH based algorithms can be made fair, without a significant loss in efficiency. Specifically, we show an algorithm that reports a point in the $r$-neighborhood of a query $q$ with almost uniform probability. The query time is proportional to $O\bigl( \mathrm{dns}(q.r) \dsQ(n,c) \bigr)$, and its space is $O(\dsS(n,c))$, where $\dsQ(n,c)$ and $\dsS(n,c)$ are the query time and space of an LSH algorithm for $c$-approximate near neighbor, and $\mathrm{dns}(q,r)$ is a function of the local density around $q$. Our approach works more generally for sampling uniformly from a sub-collection of sets of a given collection and can be used in a few other applications. Finally, we run experiments to show performance of our approach on real data. |
| Tasks | |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02640v2 |
| https://arxiv.org/pdf/1906.02640v2.pdf | |
| PWC | https://paperswithcode.com/paper/near-neighbor-who-is-the-fairest-of-them-all |
| Repo | |
| Framework | |
The Ethics of AI Ethics – An Evaluation of Guidelines
| Title | The Ethics of AI Ethics – An Evaluation of Guidelines |
| Authors | Thilo Hagendorff |
| Abstract | Current advances in research, development and application of artificial intelligence (AI) systems have yielded a far-reaching discourse on AI ethics. In consequence, a number of ethics guidelines have been released in recent years. These guidelines comprise normative principles and recommendations aimed to harness the “disruptive” potentials of new AI technologies. Designed as a comprehensive evaluation, this paper analyzes and compares these guidelines highlighting overlaps but also omissions. As a result, I give a detailed overview of the field of AI ethics. Finally, I also examine to what extent the respective ethical principles and values are implemented in the practice of research, development and application of AI systems - and how the effectiveness in the demands of AI ethics can be improved. |
| Tasks | |
| Published | 2019-02-28 |
| URL | https://arxiv.org/abs/1903.03425v2 |
| https://arxiv.org/pdf/1903.03425v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-ethics-of-ai-ethics-an-evaluation-of |
| Repo | |
| Framework | |
A Transformer with Interleaved Self-attention and Convolution for Hybrid Acoustic Models
| Title | A Transformer with Interleaved Self-attention and Convolution for Hybrid Acoustic Models |
| Authors | Liang Lu |
| Abstract | Transformer with self-attention has achieved great success in the area of nature language processing. Recently, there have been a few studies on transformer for end-to-end speech recognition, while its application for hybrid acoustic model is still very limited. In this paper, we revisit the transformer-based hybrid acoustic model, and propose a model structure with interleaved self-attention and 1D convolution, which is proven to have faster convergence and higher recognition accuracy. We also study several aspects of the transformer model, including the impact of the positional encoding feature, dropout regularization, as well as training with and without time restriction. We show competitive recognition results on the public Librispeech dataset when compared to the Kaldi baseline at both cross entropy training and sequence training stages. For reproducible research, we release our source code and recipe within the PyKaldi2 toolbox. |
| Tasks | End-To-End Speech Recognition, Speech Recognition |
| Published | 2019-10-23 |
| URL | https://arxiv.org/abs/1910.10352v1 |
| https://arxiv.org/pdf/1910.10352v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-transformer-with-interleaved-self-attention |
| Repo | |
| Framework | |
AIM 2019 Challenge on Image Demoireing: Methods and Results
| Title | AIM 2019 Challenge on Image Demoireing: Methods and Results |
| Authors | Shanxin Yuan, Radu Timofte, Gregory Slabaugh, Ales Leonardis, Bolun Zheng, Xin Ye, Xiang Tian, Yaowu Chen, Xi Cheng, Zhenyong Fu, Jian Yang, Ming Hong, Wenying Lin, Wenjin Yang, Yanyun Qu, Hong-Kyu Shin, Joon-Yeon Kim, Sung-Jea Ko, Hang Dong, Yu Guo, Jie Wang, Xuan Ding, Zongyan Han, Sourya Dipta Das, Kuldeep Purohit, Praveen Kandula, Maitreya Suin, A. N. Rajagopalan |
| Abstract | This paper reviews the first-ever image demoireing challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ICCV 2019. This paper describes the challenge, and focuses on the proposed solutions and their results. Demoireing is a difficult task of removing moire patterns from an image to reveal an underlying clean image. A new dataset, called LCDMoire was created for this challenge, and consists of 10,200 synthetically generated image pairs (moire and clean ground truth). The challenge was divided into 2 tracks. Track 1 targeted fidelity, measuring the ability of demoire methods to obtain a moire-free image compared with the ground truth, while Track 2 examined the perceptual quality of demoire methods. The tracks had 60 and 39 registered participants, respectively. A total of eight teams competed in the final testing phase. The entries span the current the state-of-the-art in the image demoireing problem. |
| Tasks | |
| Published | 2019-11-08 |
| URL | https://arxiv.org/abs/1911.03461v1 |
| https://arxiv.org/pdf/1911.03461v1.pdf | |
| PWC | https://paperswithcode.com/paper/aim-2019-challenge-on-image-demoireing-1 |
| Repo | |
| Framework | |
