Paper Group ANR 815
Deep Learning based Cephalometric Landmark Identification using Landmark-dependent Multi-scale Patches. PILS: Exploring high-order neighborhoods by pattern mining and injection. Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving. A novel classification-selection approach for the self updating of template-based face recognition syst …
Deep Learning based Cephalometric Landmark Identification using Landmark-dependent Multi-scale Patches
| Title | Deep Learning based Cephalometric Landmark Identification using Landmark-dependent Multi-scale Patches |
| Authors | Chonho Lee, Chihiro Tanikawa, Jae-Yeon Lim, Takashi Yamashiro |
| Abstract | A deep neural network based cephalometric landmark identification model is proposed. Two neural networks, named patch classification and point estimation, are trained by multi-scale image patches cropped from 935 Cephalograms (of Japanese young patients), whose size and orientation vary based on landmark-dependent criteria examined by orthodontists. The proposed model identifies both 22 hard and 11 soft tissue landmarks. In order to evaluate the proposed model, (i) landmark estimation accuracy by Euclidean distance error between true and estimated values, and (ii) success rate that the estimated landmark was located within the corresponding norm using confidence ellipse, are computed. The proposed model successfully identified hard tissue landmarks within the error range of 1.32 - 3.5 mm and with a mean success rate of 96.4%, and soft tissue landmarks with the error range of 1.16 - 4.37 mm and with a mean success rate of 75.2%. We verify that considering the landmark-dependent size and orientation of patches helps improve the estimation accuracy. |
| Tasks | |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.02961v1 |
| https://arxiv.org/pdf/1906.02961v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-based-cephalometric-landmark |
| Repo | |
| Framework | |
PILS: Exploring high-order neighborhoods by pattern mining and injection
| Title | PILS: Exploring high-order neighborhoods by pattern mining and injection |
| Authors | Florian Arnold, Ítalo Santana, Kenneth Sörensen, Thibaut Vidal |
| Abstract | We introduce pattern injection local search (PILS), an optimization strategy that uses pattern mining to explore high-order local-search neighborhoods, and illustrate its application on the vehicle routing problem. PILS operates by storing a limited number of frequent patterns from elite solutions. During the local search, each pattern is used to define one move in which 1) incompatible edges are disconnected, 2) the edges defined by the pattern are reconnected, and 3) the remaining solution fragments are optimally reconnected. Each such move is accepted only in case of solution improvement. As visible in our experiments, this strategy results in a new paradigm of local search, which complements and enhances classical search approaches in a controllable amount of computational time. We demonstrate that PILS identifies useful high-order moves (e.g., 9-opt and 10-opt) which would otherwise not be found by enumeration, and that it significantly improves the performance of state-of-the-art population-based and neighborhood-centered metaheuristics. |
| Tasks | |
| Published | 2019-12-24 |
| URL | https://arxiv.org/abs/1912.11462v1 |
| https://arxiv.org/pdf/1912.11462v1.pdf | |
| PWC | https://paperswithcode.com/paper/pils-exploring-high-order-neighborhoods-by |
| Repo | |
| Framework | |
Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving
| Title | Yes, we GAN: Applying Adversarial Techniques for Autonomous Driving |
| Authors | Michal Uricar, Pavel Krizek, David Hurych, Ibrahim Sobh, Senthil Yogamani, Patrick Denny |
| Abstract | Generative Adversarial Networks (GAN) have gained a lot of popularity from their introduction in 2014 till present. Research on GAN is rapidly growing and there are many variants of the original GAN focusing on various aspects of deep learning. GAN are perceived as the most impactful direction of machine learning in the last decade. This paper focuses on the application of GAN in autonomous driving including topics such as advanced data augmentation, loss function learning, semi-supervised learning, etc. We formalize and review key applications of adversarial techniques and discuss challenges and open problems to be addressed. |
| Tasks | Autonomous Driving, Data Augmentation |
| Published | 2019-02-09 |
| URL | https://arxiv.org/abs/1902.03442v2 |
| https://arxiv.org/pdf/1902.03442v2.pdf | |
| PWC | https://paperswithcode.com/paper/yes-we-gan-applying-adversarial-techniques |
| Repo | |
| Framework | |
A novel classification-selection approach for the self updating of template-based face recognition systems
| Title | A novel classification-selection approach for the self updating of template-based face recognition systems |
| Authors | Giulia Orrù, Gian Luca Marcialis, Fabio Roli |
| Abstract | The boosting on the need of security notably increased the amount of possible facial recognition applications, especially due to the success of the Internet of Things (IoT) paradigm. However, although handcrafted and deep learning-inspired facial features reached a significant level of compactness and expressive power, the facial recognition performance still suffers from intra-class variations such as ageing, facial expressions, lighting changes, and pose. These variations cannot be captured in a single acquisition and require multiple acquisitions of long duration, which are expensive and need a high level of collaboration from the users. Among others, self-update algorithms have been proposed in order to mitigate these problems. Self-updating aims to add novel templates to the users’ gallery among the inputs submitted during system operations. Consequently, computational complexity and storage space tend to be among the critical requirements of these algorithms. The present paper deals with the above problems by a novel template-based self-update algorithm, able to keep over time the expressive power of a limited set of templates stored in the system database. The rationale behind the proposed approach is in the working hypothesis that a dominating mode characterises the features’ distribution given the client. Therefore, the key point is to select the best templates around that mode. We propose two methods, which are tested on systems based on handcrafted features and deep-learning-inspired autoencoders at the state-of-the-art. Three benchmark data sets are used. Experimental results confirm that, by effective and compact feature sets which can support our working hypothesis, the proposed classification-selection approaches overcome the problem of manual updating and, in case, stringent computational requirements. |
| Tasks | Face Recognition |
| Published | 2019-11-28 |
| URL | https://arxiv.org/abs/1911.12688v1 |
| https://arxiv.org/pdf/1911.12688v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-novel-classification-selection-approach-for |
| Repo | |
| Framework | |
Learning with Multiplicative Perturbations
| Title | Learning with Multiplicative Perturbations |
| Authors | Xiulong Yang, Shihao Ji |
| Abstract | Adversarial Training (AT) and Virtual Adversarial Training (VAT) are the regularization techniques that train Deep Neural Networks (DNNs) with adversarial examples generated by adding small but worst-case perturbations to input examples. In this paper, we propose xAT and xVAT, new adversarial training algorithms, that generate \textbf{multiplicative} perturbations to input examples for robust training of DNNs. Such perturbations are much more perceptible and interpretable than their \textbf{additive} counterparts exploited by AT and VAT. Furthermore, the multiplicative perturbations can be generated transductively or inductively while the standard AT and VAT only support a transductive implementation. We conduct a series of experiments that analyze the behavior of the multiplicative perturbations and demonstrate that xAT and xVAT match or outperform state-of-the-art classification accuracies across multiple established benchmarks while being about 30% faster than their additive counterparts. Furthermore, the resulting DNNs also demonstrate distinct weight distributions. |
| Tasks | |
| Published | 2019-12-04 |
| URL | https://arxiv.org/abs/1912.01810v1 |
| https://arxiv.org/pdf/1912.01810v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-with-multiplicative-perturbations |
| Repo | |
| Framework | |
Training generative networks using random discriminators
| Title | Training generative networks using random discriminators |
| Authors | Babak Barazandeh, Meisam Razaviyayn, Maziar Sanjabi |
| Abstract | In recent years, Generative Adversarial Networks (GANs) have drawn a lot of attentions for learning the underlying distribution of data in various applications. Despite their wide applicability, training GANs is notoriously difficult. This difficulty is due to the min-max nature of the resulting optimization problem and the lack of proper tools of solving general (non-convex, non-concave) min-max optimization problems. In this paper, we try to alleviate this problem by proposing a new generative network that relies on the use of random discriminators instead of adversarial design. This design helps us to avoid the min-max formulation and leads to an optimization problem that is stable and could be solved efficiently. The performance of the proposed method is evaluated using handwritten digits (MNIST) and Fashion products (Fashion-MNIST) data sets. While the resulting images are not as sharp as adversarial training, the use of random discriminator leads to a much faster algorithm as compared to the adversarial counterpart. This observation, at the minimum, illustrates the potential of the random discriminator approach for warm-start in training GANs. |
| Tasks | |
| Published | 2019-04-22 |
| URL | http://arxiv.org/abs/1904.09775v1 |
| http://arxiv.org/pdf/1904.09775v1.pdf | |
| PWC | https://paperswithcode.com/paper/training-generative-networks-using-random |
| Repo | |
| Framework | |
Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification
| Title | Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification |
| Authors | Zhi-Xiu Ye, Zhen-Hua Ling |
| Abstract | This paper presents a multi-level matching and aggregation network (MLMAN) for few-shot relation classification. Previous studies on this topic adopt prototypical networks, which calculate the embedding vector of a query instance and the prototype vector of each support set independently. In contrast, our proposed MLMAN model encodes the query instance and each support set in an interactive way by considering their matching information at both local and instance levels. The final class prototype for each support set is obtained by attentive aggregation over the representations of its support instances, where the weights are calculated using the query instance. Experimental results demonstrate the effectiveness of our proposed methods, which achieve a new state-of-the-art performance on the FewRel dataset. |
| Tasks | Few-Shot Relation Classification, Relation Classification |
| Published | 2019-06-16 |
| URL | https://arxiv.org/abs/1906.06678v1 |
| https://arxiv.org/pdf/1906.06678v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-level-matching-and-aggregation-network |
| Repo | |
| Framework | |
Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation
| Title | Coupled Generative Adversarial Network for Continuous Fine-grained Action Segmentation |
| Authors | Harshala Gammulle, Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes |
| Abstract | We propose a novel conditional GAN (cGAN) model for continuous fine-grained human action segmentation, that utilises multi-modal data and learned scene context information. The proposed approach utilises two GANs: termed Action GAN and Auxiliary GAN, where the Action GAN is trained to operate over the current RGB frame while the Auxiliary GAN utilises supplementary information such as depth or optical flow. The goal of both GANs is to generate similar `action codes’, a vector representation of the current action. To facilitate this process a context extractor that incorporates data and recent outputs from both modes is used to extract context information to aid recognition. The result is a recurrent GAN architecture which learns a task specific loss function from multiple feature modalities. Extensive evaluations on variants of the proposed model to show the importance of utilising different information streams such as context and auxiliary information in the proposed network; and show that our model is capable of outperforming state-of-the-art methods for three widely used datasets: 50 Salads, MERL Shopping and Georgia Tech Egocentric Activities, comprising both static and dynamic camera settings. | |
| Tasks | action segmentation, Optical Flow Estimation |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09283v1 |
| https://arxiv.org/pdf/1909.09283v1.pdf | |
| PWC | https://paperswithcode.com/paper/coupled-generative-adversarial-network-for |
| Repo | |
| Framework | |
Sentence Meta-Embeddings for Unsupervised Semantic Textual Similarity
| Title | Sentence Meta-Embeddings for Unsupervised Semantic Textual Similarity |
| Authors | Nina Poerner, Ulli Waltinger, Hinrich Schütze |
| Abstract | We address the task of unsupervised Semantic Textual Similarity (STS) by ensembling diverse pre-trained sentence encoders into sentence meta-embeddings. We apply and extend different meta-embedding methods from the word embedding literature, including dimensionality reduction (Yin and Sch"utze, 2016), generalized Canonical Correlation Analysis (Rastogi et al., 2015) and cross-view autoencoders (Bollegala and Bao, 2018). We set a new unsupervised State of The Art (SoTA) on the STS Benchmark and on the STS12-STS16 datasets, with gains of between 3.7% and 6.4% Pearson’s r over single-source systems. |
| Tasks | Dimensionality Reduction, Semantic Textual Similarity |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03700v1 |
| https://arxiv.org/pdf/1911.03700v1.pdf | |
| PWC | https://paperswithcode.com/paper/sentence-meta-embeddings-for-unsupervised |
| Repo | |
| Framework | |
Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality
| Title | Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicality |
| Authors | Eric Nalisnick, Akihiro Matsukawa, Yee Whye Teh, Balaji Lakshminarayanan |
| Abstract | Recent work has shown that deep generative models can assign higher likelihood to out-of-distribution data sets than to their training data (Nalisnick et al., 2019; Choi et al., 2019). We posit that this phenomenon is caused by a mismatch between the model’s typical set and its areas of high probability density. In-distribution inputs should reside in the former but not necessarily in the latter, as previous work has presumed. To determine whether or not inputs reside in the typical set, we propose a statistically principled, easy-to-implement test using the empirical distribution of model likelihoods. The test is model agnostic and widely applicable, only requiring that the likelihood can be computed or closely approximated. We report experiments showing that our procedure can successfully detect the out-of-distribution sets in several of the challenging cases reported by Nalisnick et al. (2019). |
| Tasks | |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.02994v2 |
| https://arxiv.org/pdf/1906.02994v2.pdf | |
| PWC | https://paperswithcode.com/paper/detecting-out-of-distribution-inputs-to-deep |
| Repo | |
| Framework | |
Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement
| Title | Uncertainty Quantification in Deep Learning for Safer Neuroimage Enhancement |
| Authors | Ryutaro Tanno, Daniel Worrall, Enrico Kaden, Aurobrata Ghosh, Francesco Grussu, Alberto Bizzi, Stamatios N. Sotiropoulos, Antonio Criminisi, Daniel C. Alexander |
| Abstract | Deep learning (DL) has shown great potential in medical image enhancement problems, such as super-resolution or image synthesis. However, to date, little consideration has been given to uncertainty quantification over the output image. Here we introduce methods to characterise different components of uncertainty in such problems and demonstrate the ideas using diffusion MRI super-resolution. Specifically, we propose to account for $intrinsic$ uncertainty through a heteroscedastic noise model and for $parameter$ uncertainty through approximate Bayesian inference, and integrate the two to quantify $predictive$ uncertainty over the output image. Moreover, we introduce a method to propagate the predictive uncertainty on a multi-channelled image to derived scalar parameters, and separately quantify the effects of intrinsic and parameter uncertainty therein. The methods are evaluated for super-resolution of two different signal representations of diffusion MR images—DTIs and Mean Apparent Propagator MRI—and their derived quantities such as MD and FA, on multiple datasets of both healthy and pathological human brains. Results highlight three key benefits of uncertainty modelling for improving the safety of DL-based image enhancement systems. Firstly, incorporating uncertainty improves the predictive performance even when test data departs from training data. Secondly, the predictive uncertainty highly correlates with errors, and is therefore capable of detecting predictive “failures”. Results demonstrate that such an uncertainty measure enables subject-specific and voxel-wise risk assessment of the output images. Thirdly, we show that the method for decomposing predictive uncertainty into its independent sources provides high-level “explanations” for the performance by quantifying how much uncertainty arises from the inherent difficulty of the task or the limited training examples. |
| Tasks | Bayesian Inference, Image Enhancement, Image Generation, Super-Resolution |
| Published | 2019-07-31 |
| URL | https://arxiv.org/abs/1907.13418v1 |
| https://arxiv.org/pdf/1907.13418v1.pdf | |
| PWC | https://paperswithcode.com/paper/uncertainty-quantification-in-deep-learning |
| Repo | |
| Framework | |
Next Priority Concept: A new and generic algorithm computing concepts from complex and heterogeneous data
| Title | Next Priority Concept: A new and generic algorithm computing concepts from complex and heterogeneous data |
| Authors | Christophe Demko, Karell Bertet, Cyril Faucher, Jean-François Viaud, Sergeï Kuznetsov |
| Abstract | In this article, we present a new data type agnostic algorithm calculating a concept lattice from heterogeneous and complex data. Our NextPriorityConcept algorithm is first introduced and proved in the binary case as an extension of Bordat’s algorithm with the notion of strategies to select only some predecessors of each concept, avoiding the generation of unreasonably large lattices. The algorithm is then extended to any type of data in a generic way. It is inspired from pattern structure theory, where data are locally described by predicates independent of their types, allowing the management of heterogeneous data. |
| Tasks | |
| Published | 2019-12-20 |
| URL | https://arxiv.org/abs/1912.11038v1 |
| https://arxiv.org/pdf/1912.11038v1.pdf | |
| PWC | https://paperswithcode.com/paper/next-priority-concept-a-new-and-generic |
| Repo | |
| Framework | |
Image Enhancement by Recurrently-trained Super-resolution Network
| Title | Image Enhancement by Recurrently-trained Super-resolution Network |
| Authors | Saem Park, Nojun Kwak |
| Abstract | We introduce a new learning strategy for image enhancement by recurrently training the same simple superresolution (SR) network multiple times. After initially training an SR network by using pairs of a corrupted low resolution (LR) image and an original image, the proposed method makes use of the trained SR network to generate new high resolution (HR) images with a doubled resolution from the original uncorrupted images. Then, the new HR images are downscaled to the original resolution, which work as target images for the SR network in the next stage. The newly generated HR images by the repeatedly trained SR network show better image quality and this strategy of training LR to mimic new HR can lead to a more efficient SR network. Up to a certain point, by repeating this process multiple times, better and better images are obtained. This recurrent leaning strategy for SR can be a good solution for downsizing convolution networks and making a more efficient SR network. To measure the enhanced image quality, for the first time in this area of super-resolution and image enhancement, we use VIQET MOS score which reflects human visual quality more accurately than the conventional MSE measure. |
| Tasks | Image Enhancement, Super-Resolution |
| Published | 2019-07-26 |
| URL | https://arxiv.org/abs/1907.11341v1 |
| https://arxiv.org/pdf/1907.11341v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-enhancement-by-recurrently-trained |
| Repo | |
| Framework | |
A Fusion Adversarial Underwater Image Enhancement Network with a Public Test Dataset
| Title | A Fusion Adversarial Underwater Image Enhancement Network with a Public Test Dataset |
| Authors | Hanyu Li, Jingjing Li, Wei Wang |
| Abstract | Underwater image enhancement algorithms have attracted much attention in underwater vision task. However, these algorithms are mainly evaluated on different data sets and different metrics. In this paper, we set up an effective and pubic underwater test dataset named U45 including the color casts, low contrast and haze-like effects of underwater degradation and propose a fusion adversarial network for enhancing underwater images. Meanwhile, the well-designed the adversarial loss including Lgt loss and Lfe loss is presented to focus on image features of ground truth, and image features of the image enhanced by fusion enhance method, respectively. The proposed network corrects color casts effectively and owns faster testing time with fewer parameters. Experiment results on U45 dataset demonstrate that the proposed method achieves better or comparable performance than the other state-of-the-art methods in terms of qualitative and quantitative evaluations. Moreover, an ablation study demonstrates the contributions of each component, and the application test further shows the effectiveness of the enhanced images. |
| Tasks | Image Enhancement |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.06819v2 |
| https://arxiv.org/pdf/1906.06819v2.pdf | |
| PWC | https://paperswithcode.com/paper/a-fusion-adversarial-network-for-underwater |
| Repo | |
| Framework | |
Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learning
| Title | Iteratively-Refined Interactive 3D Medical Image Segmentation with Multi-Agent Reinforcement Learning |
| Authors | Xuan Liao, Wenhao Li, Qisen Xu, Xiangfeng Wang, Bo Jin, Xiaoyun Zhang, Ya Zhang, Yanfeng Wang |
| Abstract | Existing automatic 3D image segmentation methods usually fail to meet the clinic use. Many studies have explored an interactive strategy to improve the image segmentation performance by iteratively incorporating user hints. However, the dynamic process for successive interactions is largely ignored. We here propose to model the dynamic process of iterative interactive image segmentation as a Markov decision process (MDP) and solve it with reinforcement learning (RL). Unfortunately, it is intractable to use single-agent RL for voxel-wise prediction due to the large exploration space. To reduce the exploration space to a tractable size, we treat each voxel as an agent with a shared voxel-level behavior strategy so that it can be solved with multi-agent reinforcement learning. An additional advantage of this multi-agent model is to capture the dependency among voxels for segmentation task. Meanwhile, to enrich the information of previous segmentations, we reserve the prediction uncertainty in the state space of MDP and derive an adjustment action space leading to a more precise and finer segmentation. In addition, to improve the efficiency of exploration, we design a relative cross-entropy gain-based reward to update the policy in a constrained direction. Experimental results on various medical datasets have shown that our method significantly outperforms existing state-of-the-art methods, with the advantage of fewer interactions and a faster convergence. |
| Tasks | Medical Image Segmentation, Multi-agent Reinforcement Learning, Semantic Segmentation |
| Published | 2019-11-23 |
| URL | https://arxiv.org/abs/1911.10334v1 |
| https://arxiv.org/pdf/1911.10334v1.pdf | |
| PWC | https://paperswithcode.com/paper/iteratively-refined-interactive-3d-medical |
| Repo | |
| Framework | |
