Paper Group ANR 671
On-line learning dynamics of ReLU neural networks using statistical physics techniques. Virtual Ground Truth, and Pre-selection of 3D Interest Points for Improved Repeatability Evaluation of 2D Detectors. A new Backdoor Attack in CNNs by training set corruption without label poisoning. Kernel Mean Embedding of Instance-wise Predictions in Multiple …
On-line learning dynamics of ReLU neural networks using statistical physics techniques
| Title | On-line learning dynamics of ReLU neural networks using statistical physics techniques |
| Authors | Michiel Straat, Michael Biehl |
| Abstract | We introduce exact macroscopic on-line learning dynamics of two-layer neural networks with ReLU units in the form of a system of differential equations, using techniques borrowed from statistical physics. For the first experiments, numerical solutions reveal similar behavior compared to sigmoidal activation researched in earlier work. In these experiments the theoretical results show good correspondence with simulations. In ove-rrealizable and unrealizable learning scenarios, the learning behavior of ReLU networks shows distinctive characteristics compared to sigmoidal networks. |
| Tasks | |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1903.07378v1 |
| http://arxiv.org/pdf/1903.07378v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-line-learning-dynamics-of-relu-neural |
| Repo | |
| Framework | |
Virtual Ground Truth, and Pre-selection of 3D Interest Points for Improved Repeatability Evaluation of 2D Detectors
| Title | Virtual Ground Truth, and Pre-selection of 3D Interest Points for Improved Repeatability Evaluation of 2D Detectors |
| Authors | Simon R Lang, Martin H Luerssen, David M Powers |
| Abstract | In Computer Vision, finding simple features is performed using classifiers called interest point (IP) detectors, which are often utilised to track features as the scene changes. For 2D based classifiers it has been intuitive to measure repeated point reliability using 2D metrics given the difficulty to establish ground truth beyond 2D. The aim is to bridge the gap between 2D classifiers and 3D environments, and improve performance analysis of 2D IP classification on 3D objects. This paper builds on existing work with 3D scanned and artificial models to test conventional 2D feature detectors with the assistance of virtualised 3D scenes. Virtual space depth is leveraged in tests to perform pre-selection of closest repeatable points in both 2D and 3D contexts before repeatability is measured. This more reliable ground truth is used to analyse testing configurations with a singular and 12 model dataset across affine transforms in x, y and z rotation, as well as x,y scaling with 9 well known IP detectors. The virtual scene’s ground truth demonstrates that 3D pre-selection eliminates a large portion of false positives that are normally considered repeated in 2D configurations. The results indicate that 3D virtual environments can provide assistance in comparing the performance of conventional detectors when extending their applications to 3D environments, and can result in better classification of features when testing prospective classifiers’ performance. A ROC based informedness measure also highlights tradeoffs in 2D/3D performance compared to conventional repeatability measures. |
| Tasks | |
| Published | 2019-03-05 |
| URL | http://arxiv.org/abs/1903.01828v1 |
| http://arxiv.org/pdf/1903.01828v1.pdf | |
| PWC | https://paperswithcode.com/paper/virtual-ground-truth-and-pre-selection-of-3d |
| Repo | |
| Framework | |
A new Backdoor Attack in CNNs by training set corruption without label poisoning
| Title | A new Backdoor Attack in CNNs by training set corruption without label poisoning |
| Authors | Mauro Barni, Kassem Kallas, Benedetta Tondi |
| Abstract | Backdoor attacks against CNNs represent a new threat against deep learning systems, due to the possibility of corrupting the training set so to induce an incorrect behaviour at test time. To avoid that the trainer recognises the presence of the corrupted samples, the corruption of the training set must be as stealthy as possible. Previous works have focused on the stealthiness of the perturbation injected into the training samples, however they all assume that the labels of the corrupted samples are also poisoned. This greatly reduces the stealthiness of the attack, since samples whose content does not agree with the label can be identified by visual inspection of the training set or by running a pre-classification step. In this paper we present a new backdoor attack without label poisoning Since the attack works by corrupting only samples of the target class, it has the additional advantage that it does not need to identify beforehand the class of the samples to be attacked at test time. Results obtained on the MNIST digits recognition task and the traffic signs classification task show that backdoor attacks without label poisoning are indeed possible, thus raising a new alarm regarding the use of deep learning in security-critical applications. |
| Tasks | |
| Published | 2019-02-12 |
| URL | http://arxiv.org/abs/1902.11237v1 |
| http://arxiv.org/pdf/1902.11237v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-backdoor-attack-in-cnns-by-training-set |
| Repo | |
| Framework | |
Kernel Mean Embedding of Instance-wise Predictions in Multiple Instance Regression
| Title | Kernel Mean Embedding of Instance-wise Predictions in Multiple Instance Regression |
| Authors | Thomas Uriot |
| Abstract | In this paper, we propose an extension to an existing algorithm (instance-MIR) which tackles the multiple instance regression (MIR) problem, also known as distribution regression. The MIR setting arises when the data is a collection of bags, where each bag consists of several instances which correspond to the same and unique real-valued label. The goal of a MIR algorithm is to find a mapping from the instances of an unseen bag to its target value. The instance-MIR algorithm treats all the instances separately and maps each instance to a label. The final bag label is then taken as the mean or the median of the predictions for that given bag. While it is conceptually simple, taking a single statistic to summarize the distribution of the labels in each bag is a limitation. In spite of this performance bottleneck, the instance-MIR algorithm has been shown to be competitive when compared to the current state-of-the-art methods. We address the aforementioned issue by computing the kernel mean embeddings of the distributions of the predicted labels, for each bag, and learn a regressor from these embeddings to the bag label. We test our algorithm (instance-kme-MIR) on five real world datasets and obtain better results than the baseline instance-MIR across all the datasets, while achieving state-of-the-art results on two of the datasets. |
| Tasks | |
| Published | 2019-04-24 |
| URL | https://arxiv.org/abs/1904.10583v2 |
| https://arxiv.org/pdf/1904.10583v2.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-mean-embedding-of-instance-wise |
| Repo | |
| Framework | |
Metric on random dynamical systems with vector-valued reproducing kernel Hilbert spaces
| Title | Metric on random dynamical systems with vector-valued reproducing kernel Hilbert spaces |
| Authors | Isao Ishikawa, Akinori Tanaka, Masahiro Ikeda, Yoshinobu Kawahara |
| Abstract | Development of metrics for structural data-generating mechanisms is fundamental in machine learning and the related fields. In this paper, we give a general framework to construct metrics on random nonlinear dynamical systems, defined with the Perron-Frobenius operators in vector-valued reproducing kernel Hilbert spaces (vvRKHSs). We employ vvRKHSs to design mathematically manageable metrics and also to introduce operator-valued kernels, which enables us to handle randomness in systems. Our metric provides an extension of the existing metrics for deterministic systems, and gives a specification of the kernel maximal mean discrepancy of random processes. Moreover, by considering the time-wise independence of random processes, we clarify a connection between our metric and the independence criteria with kernels such as Hilbert-Schmidt independence criteria. We empirically illustrate our metric with synthetic data, and evaluate it in the context of the independence test for random processes. We also evaluate the performance with real time seris datas via clusering tasks. |
| Tasks | |
| Published | 2019-06-17 |
| URL | https://arxiv.org/abs/1906.06957v3 |
| https://arxiv.org/pdf/1906.06957v3.pdf | |
| PWC | https://paperswithcode.com/paper/metric-on-random-dynamical-systems-with |
| Repo | |
| Framework | |
Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation
| Title | Stay on the Path: Instruction Fidelity in Vision-and-Language Navigation |
| Authors | Vihan Jain, Gabriel Magalhaes, Alexander Ku, Ashish Vaswani, Eugene Ie, Jason Baldridge |
| Abstract | Advances in learning and representations have reinvigorated work that connects language to other modalities. A particularly exciting direction is Vision-and-Language Navigation(VLN), in which agents interpret natural language instructions and visual scenes to move through environments and reach goals. Despite recent progress, current research leaves unclear how much of a role language understanding plays in this task, especially because dominant evaluation metrics have focused on goal completion rather than the sequence of actions corresponding to the instructions. Here, we highlight shortcomings of current metrics for the Room-to-Room dataset (Anderson et al.,2018b) and propose a new metric, Coverage weighted by Length Score (CLS). We also show that the existing paths in the dataset are not ideal for evaluating instruction following because they are direct-to-goal shortest paths. We join existing short paths to form more challenging extended paths to create a new data set, Room-for-Room (R4R). Using R4R and CLS, we show that agents that receive rewards for instruction fidelity outperform agents that focus on goal completion. |
| Tasks | |
| Published | 2019-05-29 |
| URL | https://arxiv.org/abs/1905.12255v3 |
| https://arxiv.org/pdf/1905.12255v3.pdf | |
| PWC | https://paperswithcode.com/paper/stay-on-the-path-instruction-fidelity-in |
| Repo | |
| Framework | |
REMI: Mining Intuitive Referring Expressions on Knowledge Bases
| Title | REMI: Mining Intuitive Referring Expressions on Knowledge Bases |
| Authors | Luis Galárraga, Julien Delaunay, Jean-Louis Dessalles |
| Abstract | A referring expression (RE) is a description that identifies a set of instances unambiguously. Mining REs from data finds applications in natural language generation, algorithmic journalism, and data maintenance. Since there may exist multiple REs for a given set of entities, it is common to focus on the most intuitive ones, i.e., the most concise and informative. In this paper we present REMI, a system that can mine intuitive REs on large RDF knowledge bases. Our experimental evaluation shows that REMI finds REs deemed intuitive by users. Moreover we show that REMI is several orders of magnitude faster than an approach based on inductive logic programming. |
| Tasks | Text Generation |
| Published | 2019-11-04 |
| URL | https://arxiv.org/abs/1911.01157v1 |
| https://arxiv.org/pdf/1911.01157v1.pdf | |
| PWC | https://paperswithcode.com/paper/remi-mining-intuitive-referring-expressions |
| Repo | |
| Framework | |
Deep Local Global Refinement Network for Stent Analysis in IVOCT Images
| Title | Deep Local Global Refinement Network for Stent Analysis in IVOCT Images |
| Authors | Yuyu Guo |
| Abstract | Implantation of stents into coronary arteries is a common treatment option for patients with cardiovascular disease. Assessment of safety and efficacy of the stent implantation occurs via manual visual inspection of the neointimal coverage from intravascular optical coherence tomography (IVOCT) images. However, such manual assessment requires the detection of thousands of strut points within the stent. This is a challenging, tedious, and time-consuming task because the strut points usually appear as small, irregular shaped objects with inhomogeneous textures, and are often occluded by shadows, artifacts, and vessel walls. Conventional methods based on textures, edge detection, or simple classifiers for automated detection of strut points in IVOCT images have low recall and precision as they are, unable to adequately represent the visual features of the strut point for detection. In this study, we propose a local-global refinement network to integrate local-patch content with global content for strut points detection from IVOCT images. Our method densely detects the potential strut points in local image patches and then refines them according to global appearance constraints to reduce false positives. Our experimental results on a clinical dataset of 7,000 IVOCT images demonstrated that our method outperformed the state-of-the-art methods with a recall of 0.92 and precision of 0.91 for strut points detection. |
| Tasks | Edge Detection |
| Published | 2019-09-23 |
| URL | https://arxiv.org/abs/1909.10169v1 |
| https://arxiv.org/pdf/1909.10169v1.pdf | |
| PWC | https://paperswithcode.com/paper/190910169 |
| Repo | |
| Framework | |
Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings
| Title | Unsupervised Domain Adaptation for Neural Machine Translation with Domain-Aware Feature Embeddings |
| Authors | Zi-Yi Dou, Junjie Hu, Antonios Anastasopoulos, Graham Neubig |
| Abstract | The recent success of neural machine translation models relies on the availability of high quality, in-domain data. Domain adaptation is required when domain-specific data is scarce or nonexistent. Previous unsupervised domain adaptation strategies include training the model with in-domain copied monolingual or back-translated data. However, these methods use generic representations for text regardless of domain shift, which makes it infeasible for translation models to control outputs conditional on a specific domain. In this work, we propose an approach that adapts models with domain-aware feature embeddings, which are learned via an auxiliary language modeling task. Our approach allows the model to assign domain-specific representations to words and output sentences in the desired domain. Our empirical results demonstrate the effectiveness of the proposed strategy, achieving consistent improvements in multiple experimental settings. In addition, we show that combining our method with back translation can further improve the performance of the model. |
| Tasks | Domain Adaptation, Language Modelling, Machine Translation, Unsupervised Domain Adaptation |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10430v1 |
| https://arxiv.org/pdf/1908.10430v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-domain-adaptation-for-neural |
| Repo | |
| Framework | |
Detection and Tracking of Small Objects in Sparse 3D Laser Range Data
| Title | Detection and Tracking of Small Objects in Sparse 3D Laser Range Data |
| Authors | Jan Razlaw, Jan Quenzel, Sven Behnke |
| Abstract | Detection and tracking of dynamic objects is a key feature for autonomous behavior in a continuously changing environment. With the increasing popularity and capability of micro aerial vehicles (MAVs) efficient algorithms have to be utilized to enable multi object tracking on limited hardware and data provided by lightweight sensors. We present a novel segmentation approach based on a combination of median filters and an efficient pipeline for detection and tracking of small objects within sparse point clouds generated by a Velodyne VLP-16 sensor. We achieve real-time performance on a single core of our MAV hardware by exploiting the inherent structure of the data. Our approach is evaluated on simulated and real scans of in- and outdoor environments, obtaining results comparable to the state of the art. Additionally, we provide an application for filtering the dynamic and mapping the static part of the data, generating further insights into the performance of the pipeline on unlabeled data. |
| Tasks | Multi-Object Tracking, Object Tracking |
| Published | 2019-03-14 |
| URL | http://arxiv.org/abs/1903.05889v1 |
| http://arxiv.org/pdf/1903.05889v1.pdf | |
| PWC | https://paperswithcode.com/paper/detection-and-tracking-of-small-objects-in |
| Repo | |
| Framework | |
Hierarchy Neighborhood Discriminative Hashing for An Unified View of Single-Label and Multi-Label Image retrieval
| Title | Hierarchy Neighborhood Discriminative Hashing for An Unified View of Single-Label and Multi-Label Image retrieval |
| Authors | Lei Ma, Hongliang Li, Qingbo Wu, Fanman Meng, King Ngi Ngan |
| Abstract | Recently, deep supervised hashing methods have become popular for large-scale image retrieval task. To preserve the semantic similarity notion between examples, they typically utilize the pairwise supervision or the triplet supervised information for hash learning. However, these methods usually ignore the semantic class information which can help the improvement of the semantic discriminative ability of hash codes. In this paper, we propose a novel hierarchy neighborhood discriminative hashing method. Specifically, we construct a bipartite graph to build coarse semantic neighbourhood relationship between the sub-class feature centers and the embeddings features. Moreover, we utilize the pairwise supervised information to construct the fined semantic neighbourhood relationship between embeddings features. Finally, we propose a hierarchy neighborhood discriminative hashing loss to unify the single-label and multilabel image retrieval problem with a one-stream deep neural network architecture. Experimental results on two largescale datasets demonstrate that the proposed method can outperform the state-of-the-art hashing methods. |
| Tasks | Image Retrieval, Multi-Label Image Retrieval, Semantic Similarity, Semantic Textual Similarity |
| Published | 2019-01-10 |
| URL | http://arxiv.org/abs/1901.03060v2 |
| http://arxiv.org/pdf/1901.03060v2.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchy-neighborhood-discriminative-hashing |
| Repo | |
| Framework | |
Synthesis and Inpainting-Based MR-CT Registration for Image-Guided Thermal Ablation of Liver Tumors
| Title | Synthesis and Inpainting-Based MR-CT Registration for Image-Guided Thermal Ablation of Liver Tumors |
| Authors | Dongming Wei, Sahar Ahmad, Jiayu Huo, Wen Peng, Yunhao Ge, Zhong Xue, Pew-Thian Yap, Wentao Li, Dinggang Shen, Qian Wang |
| Abstract | Thermal ablation is a minimally invasive procedure for treat-ing small or unresectable tumors. Although CT is widely used for guiding ablation procedures, the contrast of tumors against surrounding normal tissues in CT images is often poor, aggravating the difficulty in accurate thermal ablation. In this paper, we propose a fast MR-CT image registration method to overlay a pre-procedural MR (pMR) image onto an intra-procedural CT (iCT) image for guiding the thermal ablation of liver tumors. By first using a Cycle-GAN model with mutual information constraint to generate synthesized CT (sCT) image from the cor-responding pMR, pre-procedural MR-CT image registration is carried out through traditional mono-modality CT-CT image registration. At the intra-procedural stage, a partial-convolution-based network is first used to inpaint the probe and its artifacts in the iCT image. Then, an unsupervised registration network is used to efficiently align the pre-procedural CT (pCT) with the inpainted iCT (inpCT) image. The final transformation from pMR to iCT is obtained by combining the two estimated transformations,i.e., (1) from the pMR image space to the pCT image space (through sCT) and (2) from the pCT image space to the iCT image space (through inpCT). Experimental results confirm that the proposed method achieves high registration accuracy with a very fast computational speed. |
| Tasks | Image Registration |
| Published | 2019-07-30 |
| URL | https://arxiv.org/abs/1907.13020v1 |
| https://arxiv.org/pdf/1907.13020v1.pdf | |
| PWC | https://paperswithcode.com/paper/synthesis-and-inpainting-based-mr-ct |
| Repo | |
| Framework | |
Delving Deep into Liver Focal Lesion Detection: A Preliminary Study
| Title | Delving Deep into Liver Focal Lesion Detection: A Preliminary Study |
| Authors | Jiechao Ma, Yingqian Chen, Yu Chen, Fengkai Wan, Sumin Xue, Ziping Li, Shiting Feng |
| Abstract | Hepatocellular carcinoma (HCC) is the second most frequent cause of malignancy-related death and is one of the diseases with the highest incidence in the world. Because the liver is the only organ in the human body that is supplied by two major vessels: the hepatic artery and the portal vein, various types of malignant tumors can spread from other organs to the liver. And due to the liver masses’ heterogeneous and diffusive shape, the tumor lesions are very difficult to be recognized, thus automatic lesion detection is necessary for the doctors with huge workloads. To assist doctors, this work uses the existing large-scale annotation medical image data to delve deep into liver lesion detection from multiple directions. To solve technical difficulties, such as the image-recognition task, traditional deep learning with convolution neural networks (CNNs) has been widely applied in recent years. However, this kind of neural network, such as Faster Regions with CNN features (R-CNN), cannot leverage the spatial information because it is applied in natural images (2D) rather than medical images (3D), such as computed tomography (CT) images. To address this issue, we propose a novel algorithm that is appropriate for liver CT imaging. Furthermore, according to radiologists’ experience in clinical diagnosis and the characteristics of CT images of liver cancer, a liver cancer-detection framework with CNN, including image processing, feature extraction, region proposal, image registration, and classification recognition, was proposed to facilitate the effective detection of liver lesions. |
| Tasks | Computed Tomography (CT), Image Registration |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10346v1 |
| https://arxiv.org/pdf/1907.10346v1.pdf | |
| PWC | https://paperswithcode.com/paper/delving-deep-into-liver-focal-lesion |
| Repo | |
| Framework | |
Whole-Sample Mapping of Cancerous and Benign Tissue Properties
| Title | Whole-Sample Mapping of Cancerous and Benign Tissue Properties |
| Authors | Lydia Neary-Zajiczek, Clara Essmann, Neil Clancy, Aiman Haider, Elena Miranda, Michael Shaw, Amir Gander, Brian Davidson, Delmiro Fernandez-Reyes, Vijay Pawar, Danail Stoyanov |
| Abstract | Structural and mechanical differences between cancerous and healthy tissue give rise to variations in macroscopic properties such as visual appearance and elastic modulus that show promise as signatures for early cancer detection. Atomic force microscopy (AFM) has been used to measure significant differences in stiffness between cancerous and healthy cells owing to its high force sensitivity and spatial resolution, however due to absorption and scattering of light, it is often challenging to accurately locate where AFM measurements have been made on a bulk tissue sample. In this paper we describe an image registration method that localizes AFM elastic stiffness measurements with high-resolution images of haematoxylin and eosin (H&E)-stained tissue to within 1.5 microns. Color RGB images are segmented into three structure types (lumen, cells and stroma) by a neural network classifier trained on ground-truth pixel data obtained through k-means clustering in HSV color space. Using the localized stiffness maps and corresponding structural information, a whole-sample stiffness map is generated with a region matching and interpolation algorithm that associates similar structures with measured stiffness values. We present results showing significant differences in stiffness between healthy and cancerous liver tissue and discuss potential applications of this technique. |
| Tasks | Image Registration |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09974v1 |
| https://arxiv.org/pdf/1907.09974v1.pdf | |
| PWC | https://paperswithcode.com/paper/whole-sample-mapping-of-cancerous-and-benign |
| Repo | |
| Framework | |
Evaluation of Distance Measures for Feature based Image Registration using AlexNet
| Title | Evaluation of Distance Measures for Feature based Image Registration using AlexNet |
| Authors | K. Kavitha, B. Thirumala Rao |
| Abstract | Image registration is a classic problem of computer vision with several applications across areas like defence, remote sensing, medicine etc. Feature based image registration methods traditionally used hand-crafted feature extraction algorithms, which detect key points in an image and describe them using a region around the point. Such features are matched using a threshold either on distances or ratio of distances computed between the feature descriptors. Evolution of deep learning, in particular convolution neural networks, has enabled researchers to address several problems of vision such as recognition, tracking, localization etc. Outputs of convolution layers or fully connected layers of CNN which has been trained for applications like visual recognition are proved to be effective when used as features in other applications such as retrieval. In this work, a deep CNN, AlexNet, is used in the place of handcrafted features for feature extraction in the first stage of image registration. However, there is a need to identify a suitable distance measure and a matching method for effective results. Several distance metrics have been evaluated in the framework of nearest neighbour and nearest neighbour ratio matching methods using benchmark dataset. Evaluation is done by comparing matching and registration performance using metrics computed from ground truth. Keywords: Distance measures; deep learning; feature detection; feature descriptor; image matching |
| Tasks | Image Registration |
| Published | 2019-07-20 |
| URL | https://arxiv.org/abs/1907.12921v1 |
| https://arxiv.org/pdf/1907.12921v1.pdf | |
| PWC | https://paperswithcode.com/paper/evaluation-of-distance-measures-for-feature |
| Repo | |
| Framework | |
