Paper Group ANR 1183
Learning to Calibrate Straight Lines for Fisheye Image Rectification. Whole-Slide Image Focus Quality: Automatic Assessment and Impact on AI Cancer Detection. Towards Evolutionary Theorem Proving for Isabelle/HOL. Anxious Depression Prediction in Real-time Social Data. Multi-Purposing Domain Adaptation Discriminators for Pseudo Labeling Confidence. …
Learning to Calibrate Straight Lines for Fisheye Image Rectification
| Title | Learning to Calibrate Straight Lines for Fisheye Image Rectification |
| Authors | Zhucun Xue, Nan Xue, Gui-Song Xia, Weiming Shen |
| Abstract | This paper presents a new deep-learning based method to simultaneously calibrate the intrinsic parameters of fisheye lens and rectify the distorted images. Assuming that the distorted lines generated by fisheye projection should be straight after rectification, we propose a novel deep neural network to impose explicit geometry constraints onto processes of the fisheye lens calibration and the distorted image rectification. In addition, considering the nonlinearity of distortion distribution in fisheye images, the proposed network fully exploits multi-scale perception to equalize the rectification effects on the whole image. To train and evaluate the proposed model, we also create a new largescale dataset labeled with corresponding distortion parameters and well-annotated distorted lines. Compared with the state-of-the-art methods, our model achieves the best published rectification quality and the most accurate estimation of distortion parameters on a large set of synthetic and real fisheye images. |
| Tasks | Calibration |
| Published | 2019-04-22 |
| URL | http://arxiv.org/abs/1904.09856v2 |
| http://arxiv.org/pdf/1904.09856v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-calibrate-straight-lines-for |
| Repo | |
| Framework | |
Whole-Slide Image Focus Quality: Automatic Assessment and Impact on AI Cancer Detection
| Title | Whole-Slide Image Focus Quality: Automatic Assessment and Impact on AI Cancer Detection |
| Authors | Timo Kohlberger, Yun Liu, Melissa Moran, Po-Hsuan, Chen, Trissia Brown, Craig H. Mermel, Jason D. Hipp, Martin C. Stumpe |
| Abstract | Digital pathology enables remote access or consults and powerful image analysis algorithms. However, the slide digitization process can create artifacts such as out-of-focus (OOF). OOF is often only detected upon careful review, potentially causing rescanning and workflow delays. Although scan-time operator screening for whole-slide OOF is feasible, manual screening for OOF affecting only parts of a slide is impractical. We developed a convolutional neural network (ConvFocus) to exhaustively localize and quantify the severity of OOF regions on digitized slides. ConvFocus was developed using our refined semi-synthetic OOF data generation process, and evaluated using real whole-slide images spanning 3 different tissue types and 3 different stain types that were digitized by two different scanners. ConvFocus’s predictions were compared with pathologist-annotated focus quality grades across 514 distinct regions representing 37,700 35x35 $\mu$m image patches, and 21 digitized “z-stack” whole-slide images that contain known OOF patterns. When compared to pathologist-graded focus quality, ConvFocus achieved Spearman rank coefficients of 0.81 and 0.94 on two scanners, and reproduced the expected OOF patterns from z-stack scanning. We also evaluated the impact of OOF on the accuracy of a state-of-the-art metastatic breast cancer detector and saw a consistent decrease in performance with increasing OOF. Comprehensive whole-slide OOF categorization could enable rescans prior to pathologist review, potentially reducing the impact of digitization focus issues on the clinical workflow. We show that the algorithm trained on our semi-synthetic OOF data generalizes well to real OOF regions across tissue types, stains, and scanners. Finally, quantitative OOF maps can flag regions that might otherwise be misclassified by image analysis algorithms, preventing OOF-induced errors. |
| Tasks | |
| Published | 2019-01-15 |
| URL | http://arxiv.org/abs/1901.04619v2 |
| http://arxiv.org/pdf/1901.04619v2.pdf | |
| PWC | https://paperswithcode.com/paper/whole-slide-image-focus-quality-automatic |
| Repo | |
| Framework | |
Towards Evolutionary Theorem Proving for Isabelle/HOL
| Title | Towards Evolutionary Theorem Proving for Isabelle/HOL |
| Authors | Yutaka Nagashima |
| Abstract | Mechanized theorem proving is becoming the basis of reliable systems programming and rigorous mathematics. Despite decades of progress in proof automation, writing mechanized proofs still requires engineers’ expertise and remains labor intensive. Recently, researchers have extracted heuristics of interactive proof development from existing large proof corpora using supervised learning. However, such existing proof corpora present only one way of proving conjectures, while there are often multiple equivalently effective ways to prove one conjecture. In this abstract, we identify challenges in discovering heuristics for automatic proof search and propose our novel approach to improve heuristics of automatic proof search in Isabelle/HOL using evolutionary computation. |
| Tasks | Automated Theorem Proving |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08468v1 |
| http://arxiv.org/pdf/1904.08468v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-evolutionary-theorem-proving-for |
| Repo | |
| Framework | |
Anxious Depression Prediction in Real-time Social Data
| Title | Anxious Depression Prediction in Real-time Social Data |
| Authors | Akshi Kumar, Aditi Sharma, Anshika Arora |
| Abstract | Mental well-being and social media have been closely related domains of study. In this research a novel model, AD prediction model, for anxious depression prediction in real-time tweets is proposed. This mixed anxiety-depressive disorder is a predominantly associated with erratic thought process, restlessness and sleeplessness. Based on the linguistic cues and user posting patterns, the feature set is defined using a 5-tuple vector <word, timing, frequency, sentiment, contrast>. An anxiety-related lexicon is built to detect the presence of anxiety indicators. Time and frequency of tweet is analyzed for irregularities and opinion polarity analytics is done to find inconsistencies in posting behaviour. The model is trained using three classifiers (multinomial na"ive bayes, gradient boosting, and random forest) and majority voting using an ensemble voting classifier is done. Preliminary results are evaluated for tweets of sampled 100 users and the proposed model achieves a classification accuracy of 85.09%. |
| Tasks | |
| Published | 2019-03-25 |
| URL | http://arxiv.org/abs/1903.10222v1 |
| http://arxiv.org/pdf/1903.10222v1.pdf | |
| PWC | https://paperswithcode.com/paper/anxious-depression-prediction-in-real-time |
| Repo | |
| Framework | |
Multi-Purposing Domain Adaptation Discriminators for Pseudo Labeling Confidence
| Title | Multi-Purposing Domain Adaptation Discriminators for Pseudo Labeling Confidence |
| Authors | Garrett Wilson, Diane J. Cook |
| Abstract | Often domain adaptation is performed using a discriminator (domain classifier) to learn domain-invariant feature representations so that a classifier trained on labeled source data will generalize well to unlabeled target data. A line of research stemming from semi-supervised learning uses pseudo labeling to directly generate “pseudo labels” for the unlabeled target data and trains a classifier on the now-labeled target data, where the samples are selected or weighted based on some measure of confidence. In this paper, we propose multi-purposing the discriminator to not only aid in producing domain-invariant representations but also to provide pseudo labeling confidence. |
| Tasks | Domain Adaptation |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07802v1 |
| https://arxiv.org/pdf/1907.07802v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-purposing-domain-adaptation |
| Repo | |
| Framework | |
Explaining Models by Propagating Shapley Values of Local Components
| Title | Explaining Models by Propagating Shapley Values of Local Components |
| Authors | Hugh Chen, Scott Lundberg, Su-In Lee |
| Abstract | In healthcare, making the best possible predictions with complex models (e.g., neural networks, ensembles/stacks of different models) can impact patient welfare. In order to make these complex models explainable, we present DeepSHAP for mixed model types, a framework for layer wise propagation of Shapley values that builds upon DeepLIFT (an existing approach for explaining neural networks). We show that in addition to being able to explain neural networks, this new framework naturally enables attributions for stacks of mixed models (e.g., neural network feature extractor into a tree model) as well as attributions of the loss. Finally, we theoretically justify a method for obtaining attributions with respect to a background distribution (under a Shapley value framework). |
| Tasks | |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1911.11888v1 |
| https://arxiv.org/pdf/1911.11888v1.pdf | |
| PWC | https://paperswithcode.com/paper/explaining-models-by-propagating-shapley |
| Repo | |
| Framework | |
BIM-assisted object recognition for the on-site autonomous robotic assembly of discrete structures
| Title | BIM-assisted object recognition for the on-site autonomous robotic assembly of discrete structures |
| Authors | Mohamed Dawod, Sean Hanna |
| Abstract | Robots-operating autonomous assembly applications in an unstructured environment require precise methods to locate the building components on site. However, the current available object detection systems are not well-optimised for construction applications, due to the tedious setups incorporated for referencing an object to a system and inability to cope with the elements imperfections. In this paper, we propose a flexible object pose estimation framework to enable robots to autonomously handle building components on-site with an error tolerance to build a specific design target without the need to sort or label them. We implemented an object recognition approach that uses the virtual representation model of all the objects found in a BIM model to autonomously search for the best-matched objects in a scene. The design layout is used to guide the robot to grasp and manipulate the found elements to build the desired structure. We verify our proposed framework by testing it in an automatic discrete wall assembly workflow. Although the precision is not as expected, we analyse the possible reasons that might cause this imprecision, which paves the path for future improvements. |
| Tasks | Object Detection, Object Recognition, Pose Estimation |
| Published | 2019-08-22 |
| URL | https://arxiv.org/abs/1908.08209v1 |
| https://arxiv.org/pdf/1908.08209v1.pdf | |
| PWC | https://paperswithcode.com/paper/bim-assisted-object-recognition-for-the-on |
| Repo | |
| Framework | |
The Impact of an Inter-rater Bias on Neural Network Training
| Title | The Impact of an Inter-rater Bias on Neural Network Training |
| Authors | Or Shwartzman, Harel Gazit, Ilan Shelef, Tammy Riklin-Raviv |
| Abstract | The problem of inter-rater variability is often discussed in the context of manual labeling of medical images. It is assumed to be bypassed by automatic model-based approaches for image segmentation which are considered `objective’, providing single, deterministic solutions. However, the emergence of data-driven approaches such as Deep Neural Networks (DNNs) and their application to supervised semantic segmentation - brought this issue of raters’ disagreement back to the front-stage. In this paper, we highlight the issue of inter-rater bias as opposed to random inter-observer variability and demonstrate its influence on DNN training, leading to different segmentation results for the same input images. In fact, lower Dice scores are calculated if training and test segmentations are of different raters. Moreover, we demonstrate that inter-rater bias in the training examples is amplified when considering the segmentation predictions for the test data. We support our findings by showing that a classifier-DNN trained to distinguish between raters based on their manual annotations performs better when the automatic segmentation predictions rather than the raters’ annotations were tested. For this study, we used the ISBI 2015 Multiple Sclerosis (MS) challenge dataset, which includes annotations by two raters with different levels of expertise. The results obtained allow us to underline a worrisome clinical implication of a DNN bias induced by an inter-rater bias during training. Specially, we show that the differences in MS-lesion load estimates increase when the volume calculations are done based on the DNNs’ segmentation predictions instead of the manual annotations used for training. | |
| Tasks | Semantic Segmentation |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.11872v1 |
| https://arxiv.org/pdf/1906.11872v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-impact-of-an-inter-rater-bias-on-neural |
| Repo | |
| Framework | |
Localization in Aerial Imagery with Grid Maps using LocGAN
| Title | Localization in Aerial Imagery with Grid Maps using LocGAN |
| Authors | Haohao Hu, Junyi Zhu, Sascha Wirges, Martin Lauer |
| Abstract | In this work, we present LocGAN, our localization approach based on a geo-referenced aerial imagery and LiDAR grid maps. Currently, most self-localization approaches relate the current sensor observations to a map generated from previously acquired data. Unfortunately, this data is not always available and the generated maps are usually sensor setup specific. Global Navigation Satellite Systems (GNSS) can overcome this problem. However, they are not always reliable especially in urban areas due to multi-path and shadowing effects. Since aerial imagery is usually available, we can use it as prior information. To match aerial images with grid maps, we use conditional Generative Adversarial Networks (cGANs) which transform aerial images to the grid map domain. The transformation between the predicted and measured grid map is estimated using a localization network (LocNet). Given the geo-referenced aerial image transformation the vehicle pose can be estimated. Evaluations performed on the data recorded in region Karlsruhe, Germany show that our LocGAN approach provides reliable global localization results. |
| Tasks | |
| Published | 2019-06-04 |
| URL | https://arxiv.org/abs/1906.01540v2 |
| https://arxiv.org/pdf/1906.01540v2.pdf | |
| PWC | https://paperswithcode.com/paper/localization-in-aerial-imagery-with-grid-maps |
| Repo | |
| Framework | |
Imitation Learning of Robot Policies by Combining Language, Vision and Demonstration
| Title | Imitation Learning of Robot Policies by Combining Language, Vision and Demonstration |
| Authors | Simon Stepputtis, Joseph Campbell, Mariano Phielipp, Chitta Baral, Heni Ben Amor |
| Abstract | In this work we propose a novel end-to-end imitation learning approach which combines natural language, vision, and motion information to produce an abstract representation of a task, which in turn is used to synthesize specific motion controllers at run-time. This multimodal approach enables generalization to a wide variety of environmental conditions and allows an end-user to direct a robot policy through verbal communication. We empirically validate our approach with an extensive set of simulations and show that it achieves a high task success rate over a variety of conditions while remaining amenable to probabilistic interpretability. |
| Tasks | Imitation Learning |
| Published | 2019-11-26 |
| URL | https://arxiv.org/abs/1911.11744v1 |
| https://arxiv.org/pdf/1911.11744v1.pdf | |
| PWC | https://paperswithcode.com/paper/imitation-learning-of-robot-policies-by |
| Repo | |
| Framework | |
A Bayesian Approach to Direct and Inverse Abstract Argumentation Problems
| Title | A Bayesian Approach to Direct and Inverse Abstract Argumentation Problems |
| Authors | Hiroyuki Kido, Beishui Liao |
| Abstract | This paper studies a fundamental mechanism of how to detect a conflict between arguments given sentiments regarding acceptability of the arguments. We introduce a concept of the inverse problem of the abstract argumentation to tackle the problem. Given noisy sets of acceptable arguments, it aims to find attack relations explaining the sets well in terms of acceptability semantics. It is the inverse of the direct problem corresponding to the traditional problem of the abstract argumentation that focuses on finding sets of acceptable arguments in terms of the semantics given an attack relation between the arguments. We give a probabilistic model handling both of the problems in a way that is faithful to the acceptability semantics. From a theoretical point of view, we show that a solution to both the direct and inverse problems is a special case of the probabilistic inference on the model. We discuss that the model provides a natural extension of the semantics to cope with uncertain attack relations distributed probabilistically. From en empirical point of view, we argue that it reasonably predicts individuals sentiments regarding acceptability of arguments. This paper contributes to lay the foundation for making acceptability semantics data-driven and to provide a way to tackle the knowledge acquisition bottleneck. |
| Tasks | Abstract Argumentation |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04319v1 |
| https://arxiv.org/pdf/1909.04319v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-bayesian-approach-to-direct-and-inverse |
| Repo | |
| Framework | |
Improved Large-margin Softmax Loss for Speaker Diarisation
| Title | Improved Large-margin Softmax Loss for Speaker Diarisation |
| Authors | Yassir Fathullah, Chao Zhang, Philip C. Woodland |
| Abstract | Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers. It is well-known that large-margin training can improve the generalisation ability to unseen data, and its use in such open-set problems has been widespread. Therefore, this paper introduces a general approach to the large-margin softmax loss without any approximations to improve the quality of speaker embeddings for diarisation. Furthermore, a novel and simple way to stabilise training, when large-margin softmax is used, is proposed. Finally, to combat the effect of overlapping speech, different training margins are used to reduce the negative effect overlapping speech has on creating discriminative embeddings. Experiments on the AMI meeting corpus show that the use of large-margin softmax significantly improves the speaker error rate (SER). By using all hyper parameters of the loss in a unified way, further improvements were achieved which reached a relative SER reduction of 24.6% over the baseline. However, by training overlapping and single speaker speech samples with different margins, the best result was achieved, giving overall a 29.5% SER reduction relative to the baseline. |
| Tasks | |
| Published | 2019-11-10 |
| URL | https://arxiv.org/abs/1911.03970v2 |
| https://arxiv.org/pdf/1911.03970v2.pdf | |
| PWC | https://paperswithcode.com/paper/improved-large-margin-softmax-loss-for |
| Repo | |
| Framework | |
More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation
| Title | More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation |
| Authors | Yunguan Fu, Maria R. Robu, Bongjin Koo, Crispin Schneider, Stijn van Laarhoven, Danail Stoyanov, Brian Davidson, Matthew J. Clarkson, Yipeng Hu |
| Abstract | Improving a semi-supervised image segmentation task has the option of adding more unlabelled images, labelling the unlabelled images or combining both, as neither image acquisition nor expert labelling can be considered trivial in most clinical applications. With a laparoscopic liver image segmentation application, we investigate the performance impact by altering the quantities of labelled and unlabelled training data, using a semi-supervised segmentation algorithm based on the mean teacher learning paradigm. We first report a significantly higher segmentation accuracy, compared with supervised learning. Interestingly, this comparison reveals that the training strategy adopted in the semi-supervised algorithm is also responsible for this observed improvement, in addition to the added unlabelled data. We then compare different combinations of labelled and unlabelled data set sizes for training semi-supervised segmentation networks, to provide a quantitative example of the practically useful trade-off between the two data planning strategies in this surgical guidance application. |
| Tasks | Semantic Segmentation |
| Published | 2019-08-20 |
| URL | https://arxiv.org/abs/1908.08035v1 |
| https://arxiv.org/pdf/1908.08035v1.pdf | |
| PWC | https://paperswithcode.com/paper/more-unlabelled-data-or-label-more-data-a |
| Repo | |
| Framework | |
Instant automatic diagnosis of diabetic retinopathy
| Title | Instant automatic diagnosis of diabetic retinopathy |
| Authors | Gwenolé Quellec, Mathieu Lamard, Bruno Lay, Alexandre Le Guilcher, Ali Erginay, Béatrice Cochener, Pascale Massin |
| Abstract | The purpose of this study is to evaluate the performance of the OphtAI system for the automatic detection of referable diabetic retinopathy (DR) and the automatic assessment of DR severity using color fundus photography. OphtAI relies on ensembles of convolutional neural networks trained to recognize eye laterality, detect referable DR and assess DR severity. The system can either process single images or full examination records. To document the automatic diagnoses, accurate heatmaps are generated. The system was developed and validated using a dataset of 763,848 images from 164,660 screening procedures from the OPHDIAT screening program. For comparison purposes, it was also evaluated in the public Messidor-2 dataset. Referable DR can be detected with an area under the ROC curve of AUC = 0.989 in the Messidor-2 dataset, using the University of Iowa’s reference standard (95% CI: 0.984-0.994). This is significantly better than the only AI system authorized by the FDA, evaluated in the exact same conditions (AUC = 0.980). OphtAI can also detect vision-threatening DR with an AUC of 0.997 (95% CI: 0.996-0.998) and proliferative DR with an AUC of 0.997 (95% CI: 0.995-0.999). The system runs in 0.3 seconds using a graphics processing unit and less than 2 seconds without. OphtAI is safer, faster and more comprehensive than the only AI system authorized by the FDA so far. Instant DR diagnosis is now possible, which is expected to streamline DR screening and to give easy access to DR screening to more diabetic patients. |
| Tasks | |
| Published | 2019-06-12 |
| URL | https://arxiv.org/abs/1906.11875v1 |
| https://arxiv.org/pdf/1906.11875v1.pdf | |
| PWC | https://paperswithcode.com/paper/instant-automatic-diagnosis-of-diabetic |
| Repo | |
| Framework | |
Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation
| Title | Learning Lightweight Pedestrian Detector with Hierarchical Knowledge Distillation |
| Authors | Rui Chen, Haizhou Ai, Chong Shang, Long Chen, Zijie Zhuang |
| Abstract | It remains very challenging to build a pedestrian detection system for real world applications, which demand for both accuracy and speed. This work presents a novel hierarchical knowledge distillation framework to learn a lightweight pedestrian detector, which significantly reduces the computational cost and still holds the high accuracy at the same time. Following the `teacher–student’ diagram that a stronger, deeper neural network can teach a lightweight network to learn better representations, we explore multiple knowledge distillation architectures and reframe this approach as a unified, hierarchical distillation framework. In particular, the proposed distillation is performed at multiple hierarchies, multiple stages in a modern detector, which empowers the student detector to learn both low-level details and high-level abstractions simultaneously. Experiment result shows that a student model trained by our framework, with 6 times compression in number of parameters, still achieves competitive performance as the teacher model on the widely used pedestrian detection benchmark. | |
| Tasks | Pedestrian Detection |
| Published | 2019-09-20 |
| URL | https://arxiv.org/abs/1909.09325v1 |
| https://arxiv.org/pdf/1909.09325v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-lightweight-pedestrian-detector-with |
| Repo | |
| Framework | |
