Paper Group ANR 234
Role of Class-specific Features in Various Classification Frameworks for Human Epithelial (HEp-2) Cell Images. FashionNet: Personalized Outfit Recommendation with Deep Neural Network. Inference Trees: Adaptive Inference with Exploration. Robust and Scalable Models of Microbiome Dynamics. Prototype Discovery using Quality-Diversity. Nested multi-ins …
Role of Class-specific Features in Various Classification Frameworks for Human Epithelial (HEp-2) Cell Images
| Title | Role of Class-specific Features in Various Classification Frameworks for Human Epithelial (HEp-2) Cell Images |
| Authors | Vibha Gupta, Arnav Bhavsar |
| Abstract | The antinuclear antibody detection with human epithelial cells is a popular approach for autoimmune diseases diagnosis. The manual evaluation demands time, effort and capital, and automation in screening can greatly aid the physicians in these respects. In this work, we employ simple, efficient and visually more interpretable, class-specific features which defined based on the visual characteristics of each class. We believe that defining features with a good visual interpretation, is indeed important in a scenario, where such an approach is used in an interactive CAD system for pathologists. Considering that problem consists of few classes, and our rather simplistic feature definitions, frameworks can be structured as hierarchies of various binary classifiers. These variants include frameworks which are earlier explored and some which are not explored for this task. We perform various experiments which include traditional texture features and demonstrate the effectiveness of class-specific features in various frameworks. We make insightful comparisons between different types of classification frameworks given their silent aspects and pros and cons over each other. We also demonstrate an experiment with only intermediates samples for testing. The proposed work yields encouraging results with respect to the state-of-the-art and highlights the role of class-specific features in different classification frameworks. |
| Tasks | |
| Published | 2018-10-30 |
| URL | http://arxiv.org/abs/1810.12690v1 |
| http://arxiv.org/pdf/1810.12690v1.pdf | |
| PWC | https://paperswithcode.com/paper/role-of-class-specific-features-in-various |
| Repo | |
| Framework | |
FashionNet: Personalized Outfit Recommendation with Deep Neural Network
| Title | FashionNet: Personalized Outfit Recommendation with Deep Neural Network |
| Authors | Tong He, Yang Hu |
| Abstract | With the rapid growth of fashion-focused social networks and online shopping, intelligent fashion recommendation is now in great need. We design algorithms which automatically suggest users outfits (e.g. a shirt, together with a skirt and a pair of high-heel shoes), that fit their personal fashion preferences. Recommending sets, each of which is composed of multiple interacted items, is relatively new to recommender systems, which usually recommend individual items to users. We explore the use of deep networks for this challenging task. Our system, dubbed FashionNet, consists of two components, a feature network for feature extraction and a matching network for compatibility computation. The former is achieved through a deep convolutional network. And for the latter, we adopt a multi-layer fully-connected network structure. We design and compare three alternative architectures for FashionNet. To achieve personalized recommendation, we develop a two-stage training strategy, which uses the fine-tuning technique to transfer a general compatibility model to a model that embeds personal preference. Experiments on a large scale data set collected from a popular fashion-focused social network validate the effectiveness of the proposed networks. |
| Tasks | Recommendation Systems |
| Published | 2018-10-04 |
| URL | http://arxiv.org/abs/1810.02443v1 |
| http://arxiv.org/pdf/1810.02443v1.pdf | |
| PWC | https://paperswithcode.com/paper/fashionnet-personalized-outfit-recommendation |
| Repo | |
| Framework | |
Inference Trees: Adaptive Inference with Exploration
| Title | Inference Trees: Adaptive Inference with Exploration |
| Authors | Tom Rainforth, Yuan Zhou, Xiaoyu Lu, Yee Whye Teh, Frank Wood, Hongseok Yang, Jan-Willem van de Meent |
| Abstract | We introduce inference trees (ITs), a new class of inference methods that build on ideas from Monte Carlo tree search to perform adaptive sampling in a manner that balances exploration with exploitation, ensures consistency, and alleviates pathologies in existing adaptive methods. ITs adaptively sample from hierarchical partitions of the parameter space, while simultaneously learning these partitions in an online manner. This enables ITs to not only identify regions of high posterior mass, but also maintain uncertainty estimates to track regions where significant posterior mass may have been missed. ITs can be based on any inference method that provides a consistent estimate of the marginal likelihood. They are particularly effective when combined with sequential Monte Carlo, where they capture long-range dependencies and yield improvements beyond proposal adaptation alone. |
| Tasks | |
| Published | 2018-06-25 |
| URL | http://arxiv.org/abs/1806.09550v1 |
| http://arxiv.org/pdf/1806.09550v1.pdf | |
| PWC | https://paperswithcode.com/paper/inference-trees-adaptive-inference-with |
| Repo | |
| Framework | |
Robust and Scalable Models of Microbiome Dynamics
| Title | Robust and Scalable Models of Microbiome Dynamics |
| Authors | Travis E. Gibson, Georg K. Gerber |
| Abstract | Microbes are everywhere, including in and on our bodies, and have been shown to play key roles in a variety of prevalent human diseases. Consequently, there has been intense interest in the design of bacteriotherapies or “bugs as drugs,” which are communities of bacteria administered to patients for specific therapeutic applications. Central to the design of such therapeutics is an understanding of the causal microbial interaction network and the population dynamics of the organisms. In this work we present a Bayesian nonparametric model and associated efficient inference algorithm that addresses the key conceptual and practical challenges of learning microbial dynamics from time series microbe abundance data. These challenges include high-dimensional (300+ strains of bacteria in the gut) but temporally sparse and non-uniformly sampled data; high measurement noise; and, nonlinear and physically non-negative dynamics. Our contributions include a new type of dynamical systems model for microbial dynamics based on what we term interaction modules, or learned clusters of latent variables with redundant interaction structure (reducing the expected number of interaction coefficients from $O(n^2)$ to $O((\log n)^2)$); a fully Bayesian formulation of the stochastic dynamical systems model that propagates measurement and latent state uncertainty throughout the model; and introduction of a temporally varying auxiliary variable technique to enable efficient inference by relaxing the hard non-negativity constraint on states. We apply our method to simulated and real data, and demonstrate the utility of our technique for system identification from limited data and gaining new biological insights into bacteriotherapy design. |
| Tasks | Time Series |
| Published | 2018-05-11 |
| URL | http://arxiv.org/abs/1805.04591v2 |
| http://arxiv.org/pdf/1805.04591v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-and-scalable-models-of-microbiome-1 |
| Repo | |
| Framework | |
Prototype Discovery using Quality-Diversity
| Title | Prototype Discovery using Quality-Diversity |
| Authors | Alexander Hagg, Alexander Asteroth, Thomas Bäck |
| Abstract | An iterative computer-aided ideation procedure is introduced, building on recent quality-diversity algorithms, which search for diverse as well as high-performing solutions. Dimensionality reduction is used to define a similarity space, in which solutions are clustered into classes. These classes are represented by prototypes, which are presented to the user for selection. In the next iteration, quality-diversity focuses on searching within the selected class. A quantitative analysis is performed on a 2D airfoil, and a more complex 3D side view mirror domain shows how computer-aided ideation can help to enhance engineers’ intuition while allowing their design decisions to influence the design process. |
| Tasks | Dimensionality Reduction |
| Published | 2018-07-25 |
| URL | http://arxiv.org/abs/1807.09488v1 |
| http://arxiv.org/pdf/1807.09488v1.pdf | |
| PWC | https://paperswithcode.com/paper/prototype-discovery-using-quality-diversity |
| Repo | |
| Framework | |
Nested multi-instance classification
| Title | Nested multi-instance classification |
| Authors | Alexander Stec, Diego Klabjan, Jean Utke |
| Abstract | There are classification tasks that take as inputs groups of images rather than single images. In order to address such situations, we introduce a nested multi-instance deep network. The approach is generic in that it is applicable to general data instances, not just images. The network has several convolutional neural networks grouped together at different stages. This primarily differs from other previous works in that we organize instances into relevant groups that are treated differently. We also introduce a method to replace instances that are missing which successfully creates neutral input instances and consistently outperforms standard fill-in methods in real world use cases. In addition, we propose a method for manual dropout when a whole group of instances is missing that allows us to use richer training data and obtain higher accuracy at the end of training. With specific pretraining, we find that the model works to great effect on our real world and pub-lic datasets in comparison to baseline methods, justifying the different treatment among groups of instances. |
| Tasks | |
| Published | 2018-08-30 |
| URL | http://arxiv.org/abs/1808.10430v1 |
| http://arxiv.org/pdf/1808.10430v1.pdf | |
| PWC | https://paperswithcode.com/paper/nested-multi-instance-classification |
| Repo | |
| Framework | |
Reasoning and Facts Explanation in Valuation Based Systems
| Title | Reasoning and Facts Explanation in Valuation Based Systems |
| Authors | S. T. Wierzchoń, M. A. Kłopotek, M. Michalewicz |
| Abstract | In the literature, the optimization problem to identify a set of composite hypotheses H, which will yield the $k$ largest $P(HS_e)$ where a composite hypothesis is an instantiation of all the nodes in the network except the evidence nodes \cite{KSy:93} is of significant interest. This problem is called “finding the $k$ Most Plausible Explanation (MPE) of a given evidence $S_e$ in a Bayesian belief network”. The problem of finding $k$ most probable hypotheses is generally NP-hard \cite{Cooper:90}. Therefore in the past various simplifications of the task by restricting $k$ (to 1 or 2), restricting the structure (e.g. to singly connected networks), or shifting the complexity to spatial domain have been investigated. A genetic algorithm is proposed in this paper to overcome some of these restrictions while stepping out from probabilistic domain onto the general Valuation based System (VBS) framework is also proposed by generalizing the genetic algorithm approach to the realm of Dempster-Shafer belief calculus. |
| Tasks | |
| Published | 2018-12-21 |
| URL | http://arxiv.org/abs/1812.09086v1 |
| http://arxiv.org/pdf/1812.09086v1.pdf | |
| PWC | https://paperswithcode.com/paper/reasoning-and-facts-explanation-in-valuation |
| Repo | |
| Framework | |
YH Technologies at ActivityNet Challenge 2018
| Title | YH Technologies at ActivityNet Challenge 2018 |
| Authors | Ting Yao, Xue Li |
| Abstract | This notebook paper presents an overview and comparative analysis of our systems designed for the following five tasks in ActivityNet Challenge 2018: temporal action proposals, temporal action localization, dense-captioning events in videos, trimmed action recognition, and spatio-temporal action localization. |
| Tasks | Action Localization, Spatio-Temporal Action Localization, Temporal Action Localization |
| Published | 2018-06-29 |
| URL | http://arxiv.org/abs/1807.00686v1 |
| http://arxiv.org/pdf/1807.00686v1.pdf | |
| PWC | https://paperswithcode.com/paper/yh-technologies-at-activitynet-challenge-2018 |
| Repo | |
| Framework | |
Cramer-Wold AutoEncoder
| Title | Cramer-Wold AutoEncoder |
| Authors | Szymon Knop, Jacek Tabor, Przemysław Spurek, Igor Podolak, Marcin Mazur, Stanisław Jastrzębski |
| Abstract | We propose a new generative model, Cramer-Wold Autoencoder (CWAE). Following WAE, we directly encourage normality of the latent space. Our paper uses also the recent idea from Sliced WAE (SWAE) model, which uses one-dimensional projections as a method of verifying closeness of two distributions. The crucial new ingredient is the introduction of a new (Cramer-Wold) metric in the space of densities, which replaces the Wasserstein metric used in SWAE. We show that the Cramer-Wold metric between Gaussian mixtures is given by a simple analytic formula, which results in the removal of sampling necessary to estimate the cost function in WAE and SWAE models. As a consequence, while drastically simplifying the optimization procedure, CWAE produces samples of a matching perceptual quality to other SOTA models. |
| Tasks | |
| Published | 2018-05-23 |
| URL | https://arxiv.org/abs/1805.09235v3 |
| https://arxiv.org/pdf/1805.09235v3.pdf | |
| PWC | https://paperswithcode.com/paper/cramer-wold-autoencoder |
| Repo | |
| Framework | |
Searching for Representative Modes on Hypergraphs for Robust Geometric Model Fitting
| Title | Searching for Representative Modes on Hypergraphs for Robust Geometric Model Fitting |
| Authors | Hanzi Wang, Guobao Xiao, Yan Yan, David Suter |
| Abstract | In this paper, we propose a simple and effective {geometric} model fitting method to fit and segment multi-structure data even in the presence of severe outliers. We cast the task of geometric model fitting as a representative mode-seeking problem on hypergraphs. Specifically, a hypergraph is firstly constructed, where the vertices represent model hypotheses and the hyperedges denote data points. The hypergraph involves higher-order similarities (instead of pairwise similarities used on a simple graph), and it can characterize complex relationships between model hypotheses and data points. {In addition, we develop a hypergraph reduction technique to remove “insignificant” vertices while retaining as many “significant” vertices as possible in the hypergraph}. Based on the {simplified hypergraph, we then propose a novel mode-seeking algorithm to search for representative modes within reasonable time. Finally, the} proposed mode-seeking algorithm detects modes according to two key elements, i.e., the weighting scores of vertices and the similarity analysis between vertices. Overall, the proposed fitting method is able to efficiently and effectively estimate the number and the parameters of model instances in the data simultaneously. Experimental results demonstrate that the proposed method achieves significant superiority over {several} state-of-the-art model fitting methods on both synthetic data and real images. |
| Tasks | |
| Published | 2018-02-04 |
| URL | http://arxiv.org/abs/1802.01129v1 |
| http://arxiv.org/pdf/1802.01129v1.pdf | |
| PWC | https://paperswithcode.com/paper/searching-for-representative-modes-on |
| Repo | |
| Framework | |
In-situ Stochastic Training of MTJ Crossbar based Neural Networks
| Title | In-situ Stochastic Training of MTJ Crossbar based Neural Networks |
| Authors | Ankit Mondal, Ankur Srivastava |
| Abstract | Owing to high device density, scalability and non-volatility, Magnetic Tunnel Junction-based crossbars have garnered significant interest for implementing the weights of an artificial neural network. The existence of only two stable states in MTJs implies a high overhead of obtaining optimal binary weights in software. We illustrate that the inherent parallelism in the crossbar structure makes it highly appropriate for in-situ training, wherein the network is taught directly on the hardware. It leads to significantly smaller training overhead as the training time is independent of the size of the network, while also circumventing the effects of alternate current paths in the crossbar and accounting for manufacturing variations in the device. We show how the stochastic switching characteristics of MTJs can be leveraged to perform probabilistic weight updates using the gradient descent algorithm. We describe how the update operations can be performed on crossbars both with and without access transistors and perform simulations on them to demonstrate the effectiveness of our techniques. The results reveal that stochastically trained MTJ-crossbar NNs achieve a classification accuracy nearly same as that of real-valued-weight networks trained in software and exhibit immunity to device variations. |
| Tasks | |
| Published | 2018-06-24 |
| URL | http://arxiv.org/abs/1806.09057v1 |
| http://arxiv.org/pdf/1806.09057v1.pdf | |
| PWC | https://paperswithcode.com/paper/in-situ-stochastic-training-of-mtj-crossbar |
| Repo | |
| Framework | |
Image Segmentation Based on Multiscale Fast Spectral Clustering
| Title | Image Segmentation Based on Multiscale Fast Spectral Clustering |
| Authors | Chongyang Zhang, Guofeng Zhu, Minxin Chen, Hong Chen, Chenjian Wu |
| Abstract | In recent years, spectral clustering has become one of the most popular clustering algorithms for image segmentation. However, it has restricted applicability to large-scale images due to its high computational complexity. In this paper, we first propose a novel algorithm called Fast Spectral Clustering based on quad-tree decomposition. The algorithm focuses on the spectral clustering at superpixel level and its computational complexity is O(nlogn) + O(m) + O(m^(3/2)); its memory cost is O(m), where n and m are the numbers of pixels and the superpixels of a image. Then we propose Multiscale Fast Spectral Clustering by improving Fast Spectral Clustering, which is based on the hierarchical structure of the quad-tree. The computational complexity of Multiscale Fast Spectral Clustering is O(nlogn) and its memory cost is O(m). Extensive experiments on real large-scale images demonstrate that Multiscale Fast Spectral Clustering outperforms Normalized cut in terms of lower computational complexity and memory cost, with comparable clustering accuracy. |
| Tasks | Semantic Segmentation |
| Published | 2018-12-12 |
| URL | http://arxiv.org/abs/1812.04816v1 |
| http://arxiv.org/pdf/1812.04816v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-segmentation-based-on-multiscale-fast |
| Repo | |
| Framework | |
Capturing global spatial context for accurate cell classification in skin cancer histology
| Title | Capturing global spatial context for accurate cell classification in skin cancer histology |
| Authors | Konstantinos Zormpas-Petridis, Henrik Failmezger, Ioannis Roxanis, Matthew Blackledge, Yann Jamin, Yinyin Yuan |
| Abstract | The spectacular response observed in clinical trials of immunotherapy in patients with previously uncurable Melanoma, a highly aggressive form of skin cancer, calls for a better understanding of the cancer-immune interface. Computational pathology provides a unique opportunity to spatially dissect such interface on digitised pathological slides. Accurate cellular classification is a key to ensure meaningful results, but is often challenging even with state-of-art machine learning and deep learning methods. We propose a hierarchical framework, which mirrors the way pathologists perceive tumour architecture and define tumour heterogeneity to improve cell classification methods that rely solely on cell nuclei morphology. The SLIC superpixel algorithm was used to segment and classify tumour regions in low resolution H&E-stained histological images of melanoma skin cancer to provide a global context. Classification of superpixels into tumour, stroma, epidermis and lumen/white space, yielded a 97.7% training set accuracy and 95.7% testing set accuracy in 58 whole-tumour images of the TCGA melanoma dataset. The superpixel classification was projected down to high resolution images to enhance the performance of a single cell classifier, based on cell nuclear morphological features, and resulted in increasing its accuracy from 86.4% to 91.6%. Furthermore, a voting scheme was proposed to use global context as biological a priori knowledge, pushing the accuracy further to 92.8%. This study demonstrates how using the global spatial context can accurately characterise the tumour microenvironment and allow us to extend significantly beyond single-cell morphological classification. |
| Tasks | |
| Published | 2018-08-07 |
| URL | http://arxiv.org/abs/1808.02355v1 |
| http://arxiv.org/pdf/1808.02355v1.pdf | |
| PWC | https://paperswithcode.com/paper/capturing-global-spatial-context-for-accurate |
| Repo | |
| Framework | |
Understanding hand-object manipulation by modeling the contextual relationship between actions, grasp types and object attributes
| Title | Understanding hand-object manipulation by modeling the contextual relationship between actions, grasp types and object attributes |
| Authors | Minjie Cai, Kris Kitani, Yoichi Sato |
| Abstract | This paper proposes a novel method for understanding daily hand-object manipulation by developing computer vision-based techniques. Specifically, we focus on recognizing hand grasp types, object attributes and manipulation actions within an unified framework by exploring their contextual relationships. Our hypothesis is that it is necessary to jointly model hands, objects and actions in order to accurately recognize multiple tasks that are correlated to each other in hand-object manipulation. In the proposed model, we explore various semantic relationships between actions, grasp types and object attributes, and show how the context can be used to boost the recognition of each component. We also explore the spatial relationship between the hand and object in order to detect the manipulated object from hand in cluttered environment. Experiment results on all three recognition tasks show that our proposed method outperforms traditional appearance-based methods which are not designed to take into account contextual relationships involved in hand-object manipulation. The visualization and generalizability study of the learned context further supports our hypothesis. |
| Tasks | |
| Published | 2018-07-22 |
| URL | http://arxiv.org/abs/1807.08254v1 |
| http://arxiv.org/pdf/1807.08254v1.pdf | |
| PWC | https://paperswithcode.com/paper/understanding-hand-object-manipulation-by |
| Repo | |
| Framework | |
Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs
| Title | Optimal Gradient Checkpoint Search for Arbitrary Computation Graphs |
| Authors | Jianwei Feng, Dong Huang |
| Abstract | Deep Neural Networks(DNNs) require huge GPU memory when training on modern image/video databases. Unfortunately, the GPU memory in off-the-shelf devices is always finite, which limits the image resolutions and batch sizes that could be used for better DNN performance. Existing approaches to alleviate memory issue include better GPUs, distributed computation and gradient checkpointing. Among them, gradient checkpointing is a favorable approach as it focuses on trading computation for memory and does not require any upgrades on hardware. In gradient checkpointing, during forward, only a subset of intermediate tensors are stored, which are called Gradient Checkpoints (GCPs). Then during backward, extra local forwards are conducted to compute the missing tensors. The total training memory cost becomes the sum of (1) the memory cost of the gradient checkpoints and (2) the maximum memory cost of local forwards. To achieve maximal memory cut-offs, one needs optimal algorithms to select GCPs. Existing gradient checkpointing approaches rely on either manual input of GCPs or heuristics-based GCP search on linear computation graphs (LCGs), and cannot apply to arbitrary computation graphs(ACGs). In this paper, we present theories and optimal algorithms on GCP selection that, for the first time, apply to ACGs and achieve maximal memory cut-offs. Extensive experiments show that our approach constantly outperforms existing approaches on LCGs, and can cut off up-to 80% of training memory with a moderate time overhead (around 40%) on LCG and ACG DNNs, such as Alexnet, VGG, Resnet, Densenet and Inception Net. |
| Tasks | |
| Published | 2018-07-31 |
| URL | https://arxiv.org/abs/1808.00079v4 |
| https://arxiv.org/pdf/1808.00079v4.pdf | |
| PWC | https://paperswithcode.com/paper/cutting-down-training-memory-by-re-fowarding |
| Repo | |
| Framework | |
