Paper Group ANR 1005
Dissecting Person Re-identification from the Viewpoint of Viewpoint. Learning to Share and Hide Intentions using Information Regularization. Predicting Visual Context for Unsupervised Event Segmentation in Continuous Photo-streams. Measurement of exceptional motion in VR video contents for VR sickness assessment using deep convolutional autoencoder …
Dissecting Person Re-identification from the Viewpoint of Viewpoint
| Title | Dissecting Person Re-identification from the Viewpoint of Viewpoint |
| Authors | Xiaoxiao Sun, Liang Zheng |
| Abstract | Variations in visual factors such as viewpoint, pose, illumination and background, are usually viewed as important challenges in person re-identification (re-ID). In spite of acknowledging these factors to be influential, quantitative studies on how they affect a re-ID system are still lacking. To derive insights in this scientific campaign, this paper makes an early attempt in studying a particular factor, viewpoint. We narrow the viewpoint problem down to the pedestrian rotation angle to obtain focused conclusions. In this regard, this paper makes two contributions to the community. First, we introduce a large-scale synthetic data engine, PersonX. Composed of hand-crafted 3D person models, the salient characteristic of this engine is “controllable”. That is, we are able to synthesize pedestrians by setting the visual variables to arbitrary values. Second, on the 3D data engine, we quantitatively analyze the influence of pedestrian rotation angle on re-ID accuracy. Comprehensively, the person rotation angles are precisely customized from 0 to 360, allowing us to investigate its effect on the training, query, and gallery sets. Extensive experiment helps us have a deeper understanding of the fundamental problems in person re-ID. Our research also provides useful insights for dataset building and future practical usage, e.g., a person of a side view makes a better query. |
| Tasks | Person Re-Identification |
| Published | 2018-12-05 |
| URL | https://arxiv.org/abs/1812.02162v6 |
| https://arxiv.org/pdf/1812.02162v6.pdf | |
| PWC | https://paperswithcode.com/paper/dissecting-person-re-identification-from-the |
| Repo | |
| Framework | |
Learning to Share and Hide Intentions using Information Regularization
| Title | Learning to Share and Hide Intentions using Information Regularization |
| Authors | DJ Strouse, Max Kleiman-Weiner, Josh Tenenbaum, Matt Botvinick, David Schwab |
| Abstract | Learning to cooperate with friends and compete with foes is a key component of multi-agent reinforcement learning. Typically to do so, one requires access to either a model of or interaction with the other agent(s). Here we show how to learn effective strategies for cooperation and competition in an asymmetric information game with no such model or interaction. Our approach is to encourage an agent to reveal or hide their intentions using an information-theoretic regularizer. We consider both the mutual information between goal and action given state, as well as the mutual information between goal and state. We show how to optimize these regularizers in a way that is easy to integrate with policy gradient reinforcement learning. Finally, we demonstrate that cooperative (competitive) policies learned with our approach lead to more (less) reward for a second agent in two simple asymmetric information games. |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2018-08-06 |
| URL | http://arxiv.org/abs/1808.02093v2 |
| http://arxiv.org/pdf/1808.02093v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-share-and-hide-intentions-using |
| Repo | |
| Framework | |
Predicting Visual Context for Unsupervised Event Segmentation in Continuous Photo-streams
| Title | Predicting Visual Context for Unsupervised Event Segmentation in Continuous Photo-streams |
| Authors | Ana Garcia del Molino, Joo-Hwee Lim, Ah-Hwee Tan |
| Abstract | Segmenting video content into events provides semantic structures for indexing, retrieval, and summarization. Since motion cues are not available in continuous photo-streams, and annotations in lifelogging are scarce and costly, the frames are usually clustered into events by comparing the visual features between them in an unsupervised way. However, such methodologies are ineffective to deal with heterogeneous events, e.g. taking a walk, and temporary changes in the sight direction, e.g. at a meeting. To address these limitations, we propose Contextual Event Segmentation (CES), a novel segmentation paradigm that uses an LSTM-based generative network to model the photo-stream sequences, predict their visual context, and track their evolution. CES decides whether a frame is an event boundary by comparing the visual context generated from the frames in the past, to the visual context predicted from the future. We implemented CES on a new and massive lifelogging dataset consisting of more than 1.5 million images spanning over 1,723 days. Experiments on the popular EDUB-Seg dataset show that our model outperforms the state-of-the-art by over 16% in f-measure. Furthermore, CES’ performance is only 3 points below that of human annotators. |
| Tasks | |
| Published | 2018-08-07 |
| URL | http://arxiv.org/abs/1808.02289v1 |
| http://arxiv.org/pdf/1808.02289v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-visual-context-for-unsupervised |
| Repo | |
| Framework | |
Measurement of exceptional motion in VR video contents for VR sickness assessment using deep convolutional autoencoder
| Title | Measurement of exceptional motion in VR video contents for VR sickness assessment using deep convolutional autoencoder |
| Authors | Hak Gu Kim, Wissam J. Baddar, Heoun-taek Lim, Hyunwook Jeong, Yong Man Ro |
| Abstract | This paper proposes a new objective metric of exceptional motion in VR video contents for VR sickness assessment. In VR environment, VR sickness can be caused by several factors which are mismatched motion, field of view, motion parallax, viewing angle, etc. Similar to motion sickness, VR sickness can induce a lot of physical symptoms such as general discomfort, headache, stomach awareness, nausea, vomiting, fatigue, and disorientation. To address the viewing safety issues in virtual environment, it is of great importance to develop an objective VR sickness assessment method that predicts and analyses the degree of VR sickness induced by the VR content. The proposed method takes into account motion information that is one of the most important factors in determining the overall degree of VR sickness. In this paper, we detect the exceptional motion that is likely to induce VR sickness. Spatio-temporal features of the exceptional motion in the VR video content are encoded using a convolutional autoencoder. For objectively assessing the VR sickness, the level of exceptional motion in VR video content is measured by using the convolutional autoencoder as well. The effectiveness of the proposed method has been successfully evaluated by subjective assessment experiment using simulator sickness questionnaires (SSQ) in VR environment. |
| Tasks | |
| Published | 2018-04-11 |
| URL | http://arxiv.org/abs/1804.03939v1 |
| http://arxiv.org/pdf/1804.03939v1.pdf | |
| PWC | https://paperswithcode.com/paper/measurement-of-exceptional-motion-in-vr-video |
| Repo | |
| Framework | |
Convolutional neural networks for chemical-disease relation extraction are improved with character-based word embeddings
| Title | Convolutional neural networks for chemical-disease relation extraction are improved with character-based word embeddings |
| Authors | Dat Quoc Nguyen, Karin Verspoor |
| Abstract | We investigate the incorporation of character-based word representations into a standard CNN-based relation extraction model. We experiment with two common neural architectures, CNN and LSTM, to learn word vector representations from character embeddings. Through a task on the BioCreative-V CDR corpus, extracting relationships between chemicals and diseases, we show that models exploiting the character-based word representations improve on models that do not use this information, obtaining state-of-the-art result relative to previous neural approaches. |
| Tasks | Relation Extraction, Word Embeddings |
| Published | 2018-05-27 |
| URL | http://arxiv.org/abs/1805.10586v1 |
| http://arxiv.org/pdf/1805.10586v1.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-networks-for-chemical |
| Repo | |
| Framework | |
Perturbation Bounds for Procrustes, Classical Scaling, and Trilateration, with Applications to Manifold Learning
| Title | Perturbation Bounds for Procrustes, Classical Scaling, and Trilateration, with Applications to Manifold Learning |
| Authors | Ery Arias-Castro, Adel Javanmard, Bruno Pelletier |
| Abstract | One of the common tasks in unsupervised learning is dimensionality reduction, where the goal is to find meaningful low-dimensional structures hidden in high-dimensional data. Sometimes referred to as manifold learning, this problem is closely related to the problem of localization, which aims at embedding a weighted graph into a low-dimensional Euclidean space. Several methods have been proposed for localization, and also manifold learning. Nonetheless, the robustness property of most of them is little understood. In this paper, we obtain perturbation bounds for classical scaling and trilateration, which are then applied to derive performance bounds for Isomap, Landmark Isomap, and Maximum Variance Unfolding. A new perturbation bound for procrustes analysis plays a key role. |
| Tasks | Dimensionality Reduction |
| Published | 2018-10-22 |
| URL | https://arxiv.org/abs/1810.09569v2 |
| https://arxiv.org/pdf/1810.09569v2.pdf | |
| PWC | https://paperswithcode.com/paper/perturbation-bounds-for-procrustes-classical |
| Repo | |
| Framework | |
EiTAKA at SemEval-2018 Task 1: An Ensemble of N-Channels ConvNet and XGboost Regressors for Emotion Analysis of Tweets
| Title | EiTAKA at SemEval-2018 Task 1: An Ensemble of N-Channels ConvNet and XGboost Regressors for Emotion Analysis of Tweets |
| Authors | Mohammed Jabreel, Antonio Moreno |
| Abstract | This paper describes our system that has been used in Task1 Affect in Tweets. We combine two different approaches. The first one called N-Stream ConvNets, which is a deep learning approach where the second one is XGboost regresseor based on a set of embedding and lexicons based features. Our system was evaluated on the testing sets of the tasks outperforming all other approaches for the Arabic version of valence intensity regression task and valence ordinal classification task. |
| Tasks | Emotion Recognition |
| Published | 2018-02-26 |
| URL | http://arxiv.org/abs/1802.09233v1 |
| http://arxiv.org/pdf/1802.09233v1.pdf | |
| PWC | https://paperswithcode.com/paper/eitaka-at-semeval-2018-task-1-an-ensemble-of |
| Repo | |
| Framework | |
Uncoupled isotonic regression via minimum Wasserstein deconvolution
| Title | Uncoupled isotonic regression via minimum Wasserstein deconvolution |
| Authors | Philippe Rigollet, Jonathan Weed |
| Abstract | Isotonic regression is a standard problem in shape-constrained estimation where the goal is to estimate an unknown nondecreasing regression function $f$ from independent pairs $(x_i, y_i)$ where $\mathbb{E}[y_i]=f(x_i), i=1, \ldots n$. While this problem is well understood both statistically and computationally, much less is known about its uncoupled counterpart where one is given only the unordered sets ${x_1, \ldots, x_n}$ and ${y_1, \ldots, y_n}$. In this work, we leverage tools from optimal transport theory to derive minimax rates under weak moments conditions on $y_i$ and to give an efficient algorithm achieving optimal rates. Both upper and lower bounds employ moment-matching arguments that are also pertinent to learning mixtures of distributions and deconvolution. |
| Tasks | |
| Published | 2018-06-27 |
| URL | http://arxiv.org/abs/1806.10648v2 |
| http://arxiv.org/pdf/1806.10648v2.pdf | |
| PWC | https://paperswithcode.com/paper/uncoupled-isotonic-regression-via-minimum |
| Repo | |
| Framework | |
Program Synthesis Through Reinforcement Learning Guided Tree Search
| Title | Program Synthesis Through Reinforcement Learning Guided Tree Search |
| Authors | Riley Simmons-Edler, Anders Miltner, Sebastian Seung |
| Abstract | Program Synthesis is the task of generating a program from a provided specification. Traditionally, this has been treated as a search problem by the programming languages (PL) community and more recently as a supervised learning problem by the machine learning community. Here, we propose a third approach, representing the task of synthesizing a given program as a Markov decision process solvable via reinforcement learning(RL). From observations about the states of partial programs, we attempt to find a program that is optimal over a provided reward metric on pairs of programs and states. We instantiate this approach on a subset of the RISC-V assembly language operating on floating point numbers, and as an optimization inspired by search-based techniques from the PL community, we combine RL with a priority search tree. We evaluate this instantiation and demonstrate the effectiveness of our combined method compared to a variety of baselines, including a pure RL ablation and a state of the art Markov chain Monte Carlo search method on this task. |
| Tasks | Program Synthesis |
| Published | 2018-06-08 |
| URL | http://arxiv.org/abs/1806.02932v1 |
| http://arxiv.org/pdf/1806.02932v1.pdf | |
| PWC | https://paperswithcode.com/paper/program-synthesis-through-reinforcement |
| Repo | |
| Framework | |
Program Synthesis from Visual Specification
| Title | Program Synthesis from Visual Specification |
| Authors | Evan Hernandez, Ara Vartanian, Xiaojin Zhu |
| Abstract | Program synthesis is the process of automatically translating a specification into computer code. Traditional synthesis settings require a formal, precise specification. Motivated by computer education applications where a student learns to code simple turtle-style drawing programs, we study a novel synthesis setting where only a noisy user-intention drawing is specified. This allows students to sketch their intended output, optionally together with their own incomplete program, to automatically produce a completed program. We formulate this synthesis problem as search in the space of programs, with the score of a state being the Hausdorff distance between the program output and the user drawing. We compare several search algorithms on a corpus consisting of real user drawings and the corresponding programs, and demonstrate that our algorithms can synthesize programs optimally satisfying the specification. |
| Tasks | Program Synthesis |
| Published | 2018-06-04 |
| URL | http://arxiv.org/abs/1806.00938v1 |
| http://arxiv.org/pdf/1806.00938v1.pdf | |
| PWC | https://paperswithcode.com/paper/program-synthesis-from-visual-specification |
| Repo | |
| Framework | |
Nature vs. Nurture: The Role of Environmental Resources in Evolutionary Deep Intelligence
| Title | Nature vs. Nurture: The Role of Environmental Resources in Evolutionary Deep Intelligence |
| Authors | Audrey G. Chung, Paul Fieguth, Alexander Wong |
| Abstract | Evolutionary deep intelligence synthesizes highly efficient deep neural networks architectures over successive generations. Inspired by the nature versus nurture debate, we propose a study to examine the role of external factors on the network synthesis process by varying the availability of simulated environmental resources. Experimental results were obtained for networks synthesized via asexual evolutionary synthesis (1-parent) and sexual evolutionary synthesis (2-parent, 3-parent, and 5-parent) using a 10% subset of the MNIST dataset. Results show that a lower environmental factor model resulted in a more gradual loss in performance accuracy and decrease in storage size. This potentially allows significantly reduced storage size with minimal to no drop in performance accuracy, and the best networks were synthesized using the lowest environmental factor models. |
| Tasks | |
| Published | 2018-02-09 |
| URL | http://arxiv.org/abs/1802.03318v1 |
| http://arxiv.org/pdf/1802.03318v1.pdf | |
| PWC | https://paperswithcode.com/paper/nature-vs-nurture-the-role-of-environmental |
| Repo | |
| Framework | |
Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
| Title | Shallow-Deep Networks: Understanding and Mitigating Network Overthinking |
| Authors | Yigitcan Kaya, Sanghyun Hong, Tudor Dumitras |
| Abstract | We characterize a prevalent weakness of deep neural networks (DNNs)—overthinking—which occurs when a DNN can reach correct predictions before its final layer. Overthinking is computationally wasteful, and it can also be destructive when, by the final layer, a correct prediction changes into a misclassification. Understanding overthinking requires studying how each prediction evolves during a DNN’s forward pass, which conventionally is opaque. For prediction transparency, we propose the Shallow-Deep Network (SDN), a generic modification to off-the-shelf DNNs that introduces internal classifiers. We apply SDN to four modern architectures, trained on three image classification tasks, to characterize the overthinking problem. We show that SDNs can mitigate the wasteful effect of overthinking with confidence-based early exits, which reduce the average inference cost by more than 50% and preserve the accuracy. We also find that the destructive effect occurs for 50% of misclassifications on natural inputs and that it can be induced, adversarially, with a recent backdooring attack. To mitigate this effect, we propose a new confusion metric to quantify the internal disagreements that will likely lead to misclassifications. |
| Tasks | Image Classification |
| Published | 2018-10-16 |
| URL | https://arxiv.org/abs/1810.07052v3 |
| https://arxiv.org/pdf/1810.07052v3.pdf | |
| PWC | https://paperswithcode.com/paper/how-to-stop-off-the-shelf-deep-neural |
| Repo | |
| Framework | |
Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis
| Title | Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis |
| Authors | Rudy Bunel, Matthew Hausknecht, Jacob Devlin, Rishabh Singh, Pushmeet Kohli |
| Abstract | Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of which adopt a sequence generation paradigm similar to neural machine translation, in which sequence-to-sequence models are trained to maximize the likelihood of known reference programs. While achieving impressive results, this strategy has two key limitations. First, it ignores Program Aliasing: the fact that many different programs may satisfy a given specification (especially with incomplete specifications such as a few input-output examples). By maximizing the likelihood of only a single reference program, it penalizes many semantically correct programs, which can adversely affect the synthesizer performance. Second, this strategy overlooks the fact that programs have a strict syntax that can be efficiently checked. To address the first limitation, we perform reinforcement learning on top of a supervised model with an objective that explicitly maximizes the likelihood of generating semantically correct programs. For addressing the second limitation, we introduce a training procedure that directly maximizes the probability of generating syntactically correct programs that fulfill the specification. We show that our contributions lead to improved accuracy of the models, especially in cases where the training data is limited. |
| Tasks | Machine Translation, Program Synthesis |
| Published | 2018-05-11 |
| URL | http://arxiv.org/abs/1805.04276v2 |
| http://arxiv.org/pdf/1805.04276v2.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-grammar-and-reinforcement-learning |
| Repo | |
| Framework | |
Recurrent neural networks for aortic image sequence segmentation with sparse annotations
| Title | Recurrent neural networks for aortic image sequence segmentation with sparse annotations |
| Authors | Wenjia Bai, Hideaki Suzuki, Chen Qin, Giacomo Tarroni, Ozan Oktay, Paul M. Matthews, Daniel Rueckert |
| Abstract | Segmentation of image sequences is an important task in medical image analysis, which enables clinicians to assess the anatomy and function of moving organs. However, direct application of a segmentation algorithm to each time frame of a sequence may ignore the temporal continuity inherent in the sequence. In this work, we propose an image sequence segmentation algorithm by combining a fully convolutional network with a recurrent neural network, which incorporates both spatial and temporal information into the segmentation task. A key challenge in training this network is that the available manual annotations are temporally sparse, which forbids end-to-end training. We address this challenge by performing non-rigid label propagation on the annotations and introducing an exponentially weighted loss function for training. Experiments on aortic MR image sequences demonstrate that the proposed method significantly improves both accuracy and temporal smoothness of segmentation, compared to a baseline method that utilises spatial information only. It achieves an average Dice metric of 0.960 for the ascending aorta and 0.953 for the descending aorta. |
| Tasks | |
| Published | 2018-08-01 |
| URL | http://arxiv.org/abs/1808.00273v1 |
| http://arxiv.org/pdf/1808.00273v1.pdf | |
| PWC | https://paperswithcode.com/paper/recurrent-neural-networks-for-aortic-image |
| Repo | |
| Framework | |
Pedestrian Collision Avoidance System (PeCAS): a Deep Learning Framework
| Title | Pedestrian Collision Avoidance System (PeCAS): a Deep Learning Framework |
| Authors | Peetak Mitra |
| Abstract | We propose a new deep learning based framework to identify pedestrians, and caution distracted drivers, in an effort to prevent the loss of life and property. This framework uses two Convolutional Neural Networks (CNN), one which detects pedestrians and the second which predicts the onset of drowsiness in a driver, is implemented on a Raspberry Pi 3 Model B+, shows great promise. The algorithm for implementing such a low-cost, low-compute model is presented and the results discussed. |
| Tasks | |
| Published | 2018-11-11 |
| URL | http://arxiv.org/abs/1811.04453v2 |
| http://arxiv.org/pdf/1811.04453v2.pdf | |
| PWC | https://paperswithcode.com/paper/pedestrian-collision-avoidance-system-pecas-a |
| Repo | |
| Framework | |
