Paper Group ANR 1044
Efficient Learning of Distributed Linear-Quadratic Controllers. Self-Supervised Convolutional Subspace Clustering Network. Unsupervised Domain Adaptation of Language Models for Reading Comprehension. Deep Instance-Level Hard Negative Mining Model for Histopathology Images. Deep Flow-Guided Video Inpainting. Automatic Image Pixel Clustering based on …
Efficient Learning of Distributed Linear-Quadratic Controllers
| Title | Efficient Learning of Distributed Linear-Quadratic Controllers |
| Authors | Salar Fattahi, Nikolai Matni, Somayeh Sojoudi |
| Abstract | In this work, we propose a robust approach to design distributed controllers for unknown-but-sparse linear and time-invariant systems. By leveraging modern techniques in distributed controller synthesis and structured linear inverse problems as applied to system identification, we show that near-optimal distributed controllers can be learned with sub-linear sample complexity and computed with near-linear time complexity, both measured with respect to the dimension of the system. In particular, we provide sharp end-to-end guarantees on the stability and the performance of the designed distributed controller and prove that for sparse systems, the number of samples needed to guarantee robust and near optimal performance of the designed controller can be significantly smaller than the dimension of the system. Finally, we show that the proposed optimization problem can be solved to global optimality with near-linear time complexity by iteratively solving a series of small quadratic programs. |
| Tasks | |
| Published | 2019-09-21 |
| URL | https://arxiv.org/abs/1909.09895v2 |
| https://arxiv.org/pdf/1909.09895v2.pdf | |
| PWC | https://paperswithcode.com/paper/190909895 |
| Repo | |
| Framework | |
Self-Supervised Convolutional Subspace Clustering Network
| Title | Self-Supervised Convolutional Subspace Clustering Network |
| Authors | Junjian Zhang, Chun-Guang Li, Chong You, Xianbiao Qi, Honggang Zhang, Jun Guo, Zhouchen Lin |
| Abstract | Subspace clustering methods based on data self-expression have become very popular for learning from data that lie in a union of low-dimensional linear subspaces. However, the applicability of subspace clustering has been limited because practical visual data in raw form do not necessarily lie in such linear subspaces. On the other hand, while Convolutional Neural Network (ConvNet) has been demonstrated to be a powerful tool for extracting discriminative features from visual data, training such a ConvNet usually requires a large amount of labeled data, which are unavailable in subspace clustering applications. To achieve simultaneous feature learning and subspace clustering, we propose an end-to-end trainable framework, called Self-Supervised Convolutional Subspace Clustering Network (S$^2$ConvSCN), that combines a ConvNet module (for feature learning), a self-expression module (for subspace clustering) and a spectral clustering module (for self-supervision) into a joint optimization framework. Particularly, we introduce a dual self-supervision that exploits the output of spectral clustering to supervise the training of the feature learning module (via a classification loss) and the self-expression module (via a spectral clustering loss). Our experiments on four benchmark datasets show the effectiveness of the dual self-supervision and demonstrate superior performance of our proposed approach. |
| Tasks | Image Clustering |
| Published | 2019-05-01 |
| URL | http://arxiv.org/abs/1905.00149v1 |
| http://arxiv.org/pdf/1905.00149v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-supervised-convolutional-subspace |
| Repo | |
| Framework | |
Unsupervised Domain Adaptation of Language Models for Reading Comprehension
| Title | Unsupervised Domain Adaptation of Language Models for Reading Comprehension |
| Authors | Kosuke Nishida, Kyosuke Nishida, Itsumi Saito, Hisako Asano, Junji Tomita |
| Abstract | This study tackles unsupervised domain adaptation of reading comprehension (UDARC). Reading comprehension (RC) is a task to learn the capability for question answering with textual sources. State-of-the-art models on RC still do not have general linguistic intelligence; i.e., their accuracy worsens for out-domain datasets that are not used in the training. We hypothesize that this discrepancy is caused by a lack of the language modeling (LM) capability for the out-domain. The UDARC task allows models to use supervised RC training data in the source domain and only unlabeled passages in the target domain. To solve the UDARC problem, we provide two domain adaptation models. The first one learns the out-domain LM and in-domain RC task sequentially. The second one is the proposed model that uses a multi-task learning approach of LM and RC. The models can retain both the RC capability acquired from the supervised data in the source domain and the LM capability from the unlabeled data in the target domain. We evaluated the models on UDARC with five datasets in different domains. The models outperformed the model without domain adaptation. In particular, the proposed model yielded an improvement of 4.3/4.2 points in EM/F1 in an unseen biomedical domain. |
| Tasks | Domain Adaptation, Language Modelling, Multi-Task Learning, Question Answering, Reading Comprehension, Unsupervised Domain Adaptation |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.10768v1 |
| https://arxiv.org/pdf/1911.10768v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-of-language |
| Repo | |
| Framework | |
Deep Instance-Level Hard Negative Mining Model for Histopathology Images
| Title | Deep Instance-Level Hard Negative Mining Model for Histopathology Images |
| Authors | Meng Li, Lin Wu, Arnold Wiliem, Kun Zhao, Teng Zhang, Brian C. Lovell |
| Abstract | Histopathology image analysis can be considered as a Multiple instance learning (MIL) problem, where the whole slide histopathology image (WSI) is regarded as a bag of instances (i.e, patches) and the task is to predict a single class label to the WSI. However, in many real-life applications such as computational pathology, discovering the key instances that trigger the bag label is of great interest because it provides reasons for the decision made by the system. In this paper, we propose a deep convolutional neural network (CNN) model that addresses the primary task of a bag classification on a WSI and also learns to identify the response of each instance to provide interpretable results to the final prediction. We incorporate the attention mechanism into the proposed model to operate the transformation of instances and learn attention weights to allow us to find key patches. To perform a balanced training, we introduce adaptive weighing in each training bag to explicitly adjust the weight distribution in order to concentrate more on the contribution of hard samples. Based on the learned attention weights, we further develop a solution to boost the classification performance by generating the bags with hard negative instances. We conduct extensive experiments on colon and breast cancer histopathology data and show that our framework achieves state-of-the-art performance. |
| Tasks | Multiple Instance Learning |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.09681v3 |
| https://arxiv.org/pdf/1906.09681v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-instance-level-hard-negative-mining |
| Repo | |
| Framework | |
Deep Flow-Guided Video Inpainting
| Title | Deep Flow-Guided Video Inpainting |
| Authors | Rui Xu, Xiaoxiao Li, Bolei Zhou, Chen Change Loy |
| Abstract | Video inpainting, which aims at filling in missing regions of a video, remains challenging due to the difficulty of preserving the precise spatial and temporal coherence of video contents. In this work we propose a novel flow-guided video inpainting approach. Rather than filling in the RGB pixels of each frame directly, we consider video inpainting as a pixel propagation problem. We first synthesize a spatially and temporally coherent optical flow field across video frames using a newly designed Deep Flow Completion network. Then the synthesized flow field is used to guide the propagation of pixels to fill up the missing regions in the video. Specifically, the Deep Flow Completion network follows a coarse-to-fine refinement to complete the flow fields, while their quality is further improved by hard flow example mining. Following the guide of the completed flow, the missing video regions can be filled up precisely. Our method is evaluated on DAVIS and YouTube-VOS datasets qualitatively and quantitatively, achieving the state-of-the-art performance in terms of inpainting quality and speed. |
| Tasks | Optical Flow Estimation, Video Inpainting |
| Published | 2019-05-08 |
| URL | https://arxiv.org/abs/1905.02884v1 |
| https://arxiv.org/pdf/1905.02884v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-flow-guided-video-inpainting |
| Repo | |
| Framework | |
Automatic Image Pixel Clustering based on Mussels Wandering Optimiz
| Title | Automatic Image Pixel Clustering based on Mussels Wandering Optimiz |
| Authors | Xin Zhong, Frank Y. Shih, Xiwang Guo |
| Abstract | Image segmentation as a clustering problem is to identify pixel groups on an image without any preliminary labels available. It remains a challenge in machine vision because of the variations in size and shape of image segments. Furthermore, determining the segment number in an image is NP-hard without prior knowledge of the image content. This paper presents an automatic color image pixel clustering scheme based on mussels wandering optimization. By applying an activation variable to determine the number of clusters along with the cluster centers optimization, an image is segmented with minimal prior knowledge and human intervention. By revising the within- and between-class sum of squares ratio for random natural image contents, we provide a novel fitness function for image pixel clustering tasks. Comprehensive empirical studies of the proposed scheme against other state-of-the-art competitors on synthetic data and the ASD dataset have demonstrated the promising performance of the proposed scheme. |
| Tasks | Semantic Segmentation |
| Published | 2019-09-08 |
| URL | https://arxiv.org/abs/1909.03380v1 |
| https://arxiv.org/pdf/1909.03380v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-image-pixel-clustering-based-on |
| Repo | |
| Framework | |
A Generative Model for Molecular Distance Geometry
| Title | A Generative Model for Molecular Distance Geometry |
| Authors | Gregor N. C. Simm, José Miguel Hernández-Lobato |
| Abstract | Computing equilibrium states for many-body systems, such as molecules, is a long-standing challenge. In the absence of methods for generating statistically independent samples, great computational effort is invested in simulating these systems using, for example, Markov chain Monte Carlo. We present a probabilistic model that generates such samples for molecules from their graph representations. Our model learns a low-dimensional manifold that preserves the geometry of local atomic neighborhoods through a principled learning representation that is based on Euclidean distance geometry. In a new benchmark for molecular conformation generation, we show experimentally that our generative model achieves state-of-the-art accuracy. Finally, we show how to use our model as a proposal distribution in an importance sampling scheme to compute molecular properties. |
| Tasks | |
| Published | 2019-09-25 |
| URL | https://arxiv.org/abs/1909.11459v3 |
| https://arxiv.org/pdf/1909.11459v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-generative-model-for-molecular-distance-1 |
| Repo | |
| Framework | |
The effect of task and training on intermediate representations in convolutional neural networks revealed with modified RV similarity analysis
| Title | The effect of task and training on intermediate representations in convolutional neural networks revealed with modified RV similarity analysis |
| Authors | Jessica A. F. Thompson, Yoshua Bengio, Marc Schoenwiesner |
| Abstract | Centered Kernel Alignment (CKA) was recently proposed as a similarity metric for comparing activation patterns in deep networks. Here we experiment with the modified RV-coefficient (RV2), which has very similar properties as CKA while being less sensitive to dataset size. We compare the representations of networks that received varying amounts of training on different layers: a standard trained network (all parameters updated at every step), a freeze trained network (layers gradually frozen during training), random networks (only some layers trained), and a completely untrained network. We found that RV2 was able to recover expected similarity patterns and provide interpretable similarity matrices that suggested hypotheses about how representations are affected by different training recipes. We propose that the superior performance achieved by freeze training can be attributed to representational differences in the penultimate layer. Our comparisons of random networks suggest that the inputs and targets serve as anchors on the representations in the lowest and highest layers. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.02260v1 |
| https://arxiv.org/pdf/1912.02260v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-effect-of-task-and-training-on |
| Repo | |
| Framework | |
Wearable Affective Life-Log System for Understanding Emotion Dynamics in Daily Life
| Title | Wearable Affective Life-Log System for Understanding Emotion Dynamics in Daily Life |
| Authors | Byung Hyung Kim, Sungho Jo |
| Abstract | Past research on recognizing human affect has made use of a variety of physiological sensors in many ways. Nonetheless, how affective dynamics are influenced in the context of human daily life has not yet been explored. In this work, we present a wearable affective life-log system (ALIS), that is robust as well as easy to use in daily life to detect emotional changes and determine their cause-and-effect relationship on users’ lives. The proposed system records how a user feels in certain situations during long-term activities with physiological sensors. Based on the long-term monitoring, the system analyzes how the contexts of the user’s life affect his/her emotion changes. Furthermore, real-world experimental results demonstrate that the proposed wearable life-log system enables us to build causal structures to find effective stress relievers suited to every stressful situation in school life. |
| Tasks | |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01072v2 |
| https://arxiv.org/pdf/1911.01072v2.pdf | |
| PWC | https://paperswithcode.com/paper/wearable-affective-life-log-system-for |
| Repo | |
| Framework | |
A unified approach to mixed-integer optimization: Nonlinear formulations and scalable algorithms
| Title | A unified approach to mixed-integer optimization: Nonlinear formulations and scalable algorithms |
| Authors | Dimitris Bertsimas, Ryan Cory-Wright, Jean Pauphilet |
| Abstract | We propose a unified framework to address a family of classical mixed-integer optimization problems, including network design, facility location, unit commitment, sparse portfolio selection, binary quadratic optimization and sparse learning problems. These problems exhibit logical relationships between continuous and discrete variables, which are usually reformulated linearly using a big-M formulation. In this work, we challenge this longstanding modeling practice and express the logical constraints in a non-linear way. By imposing a regularization condition, we reformulate these problems as convex binary optimization problems, which are solvable using an outer-approximation procedure. In numerical experiments, we establish that a general-purpose numerical strategy, which combines cutting-plane, first-order and local search methods, solves these problems faster and at a larger scale than state-of-the-art mixed-integer linear or second-order cone methods. Our approach successfully solves network design problems with 100s of nodes and provides solutions up to 40% better than the state-of-the-art; sparse portfolio selection problems with up to 3,200 securities compared with 400 securities for previous attempts; and sparse regression problems with up to 100,000 covariates. |
| Tasks | Sparse Learning |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.02109v1 |
| https://arxiv.org/pdf/1907.02109v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-approach-to-mixed-integer |
| Repo | |
| Framework | |
Relative Interior Rule in Block-Coordinate Minimization
| Title | Relative Interior Rule in Block-Coordinate Minimization |
| Authors | Tomáš Werner, Daniel Průša |
| Abstract | (Block-)coordinate minimization is an iterative optimization method which in every iteration finds a global minimum of the objective over a variable or a subset of variables, while keeping the remaining variables constant. While for some problems, coordinate minimization converges to a global minimum (e.g., convex differentiable objective), for general (non-differentiable) convex problems this may not be the case. Despite this drawback, (block-)coordinate minimization can be an acceptable option for large-scale non-differentiable convex problems; an example is methods to solve the linear programming relaxation of the discrete energy minimization problem (MAP inference in graphical models). When block-coordinate minimization is applied to a general convex problem, in every iteration the minimizer over the current coordinate block need not be unique and therefore a single minimizer must be chosen. We propose that this minimizer be chosen from the relative interior of the set of all minimizers over the current block. We show that this rule is not worse, in a certain precise sense, than any other rule. |
| Tasks | |
| Published | 2019-10-21 |
| URL | https://arxiv.org/abs/1910.09488v1 |
| https://arxiv.org/pdf/1910.09488v1.pdf | |
| PWC | https://paperswithcode.com/paper/relative-interior-rule-in-block-coordinate |
| Repo | |
| Framework | |
Aggregating Probabilistic Judgments
| Title | Aggregating Probabilistic Judgments |
| Authors | Magdalena Ivanovska, Marija Slavkovik |
| Abstract | In this paper we explore the application of methods for classical judgment aggregation in pooling probabilistic opinions on logically related issues. For this reason, we first modify the Boolean judgment aggregation framework in the way that allows handling probabilistic judgments and then define probabilistic aggregation functions obtained by generalization of the classical ones. In addition, we discuss essential desirable properties for the aggregation functions and explore impossibility results. |
| Tasks | |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09111v1 |
| https://arxiv.org/pdf/1907.09111v1.pdf | |
| PWC | https://paperswithcode.com/paper/aggregating-probabilistic-judgments |
| Repo | |
| Framework | |
Brain MRI Tumor Segmentation with Adversarial Networks
| Title | Brain MRI Tumor Segmentation with Adversarial Networks |
| Authors | Edoardo Giacomello, Daniele Loiacono, Luca Mainardi |
| Abstract | Deep Learning is a promising approach to either automate or simplify several tasks in the healthcare domain. In this work, we introduce SegAN-CAT, an approach to brain tumor segmentation in Magnetic Resonance Images (MRI), based on Adversarial Networks. In particular, we extend SegAN, successfully applied to the same task in a previous work, in two respects: (i) we used a different model input and (ii) we employed a modified loss function to train the model. We tested our approach on two large datasets, made available by the Brain Tumor Image Segmentation Benchmark (BraTS). First, we trained and tested some segmentation models assuming the availability of all the major MRI contrast modalities, i.e., T1-weighted, T1 weighted contrast-enhanced, T2-weighted, and T2-FLAIR. However, as these four modalities are not always all available for each patient, we also trained and tested four segmentation models that take as input MRIs acquired only with a single contrast modality. Finally, we proposed to apply transfer learning across different contrast modalities to improve the performance of these single-modality models. Our results are promising and show that not SegAN-CAT is able to outperform SegAN when all the four modalities are available, but also that transfer learning can actually lead to better performances when only a single modality is available. |
| Tasks | Brain Tumor Segmentation, Semantic Segmentation, Transfer Learning |
| Published | 2019-10-07 |
| URL | https://arxiv.org/abs/1910.02717v2 |
| https://arxiv.org/pdf/1910.02717v2.pdf | |
| PWC | https://paperswithcode.com/paper/transfer-brain-mri-tumor-segmentation-models |
| Repo | |
| Framework | |
Face Recognition Under Varying Blur, Illumination and Expression in an Unconstrained Environment
| Title | Face Recognition Under Varying Blur, Illumination and Expression in an Unconstrained Environment |
| Authors | Anubha Pearline. S, Hemalatha. M |
| Abstract | Face recognition system is one of the esteemed research areas in pattern recognition and computer vision as long as its major challenges. A few challenges in recognizing faces are blur, illumination, and varied expressions. Blur is natural while taking photographs using cameras, mobile phones, etc. Blur can be uniform and non-uniform. Usually non-uniform blur happens in images taken using handheld image devices. Distinguishing or handling a blurred image in a face recognition system is generally tough. Under varying lighting conditions, it is challenging to identify the person correctly. Diversified facial expressions such as happiness, sad, surprise, fear, anger changes or deforms the faces from normal images. Identifying faces with facial expressions is also a challenging task, due to the deformation caused by the facial expressions. To solve these issues, a pre-processing step was carried out after which Blur and Illumination-Robust Face recognition (BIRFR) algorithm was performed. The test image and training images with facial expression are transformed to neutral face using Facial expression removal (FER) peration. Every training image is transformed based on the optimal Transformation Spread Function (TSF), and illumination coefficients. Local Binary Pattern (LBP) features extracted from test image and transformed training image is used for classification. |
| Tasks | Face Recognition, Robust Face Recognition |
| Published | 2019-02-28 |
| URL | http://arxiv.org/abs/1902.10885v1 |
| http://arxiv.org/pdf/1902.10885v1.pdf | |
| PWC | https://paperswithcode.com/paper/face-recognition-under-varying-blur |
| Repo | |
| Framework | |
Multi-Instance Learning for End-to-End Knowledge Base Question Answering
| Title | Multi-Instance Learning for End-to-End Knowledge Base Question Answering |
| Authors | Mengxi Wei, Yifan He, Qiong Zhang, Luo Si |
| Abstract | End-to-end training has been a popular approach for knowledge base question answering (KBQA). However, real world applications often contain answers of varied quality for users’ questions. It is not appropriate to treat all available answers of a user question equally. This paper proposes a novel approach based on multiple instance learning to address the problem of noisy answers by exploring consensus among answers to the same question in training end-to-end KBQA models. In particular, the QA pairs are organized into bags with dynamic instance selection and different options of instance weighting. Curriculum learning is utilized to select instance bags during training. On the public CQA dataset, the new method significantly improves both entity accuracy and the Rouge-L score over a state-of-the-art end-to-end KBQA baseline. |
| Tasks | Knowledge Base Question Answering, Multiple Instance Learning, Question Answering |
| Published | 2019-03-06 |
| URL | http://arxiv.org/abs/1903.02652v1 |
| http://arxiv.org/pdf/1903.02652v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-instance-learning-for-end-to-end |
| Repo | |
| Framework | |
