Semantic segmentation consists in classifying each pixel of an image by assigning it to a specific label chosen from a set of all the available ones. During the last few years, a lot of attention shifted to this kind of task. Many computer vision researchers tried to apply autoencoder structures to develop models that can learn the semantics of the image as well as a low-level representation of it. In an autoencoder architecture, given an input, an encoder computes a low dimensional representation of the input that is then used by a decoder to reconstruct the original data. In this work, we propose an ensemble of convolutional neural networks (CNNs). In ensemble methods, many different models are trained and then used for classification, the ensemble aggregates the outputs of the single classifiers. The approach leverages on differences of various classifiers to improve the performance of the whole system. Diversity among the single classifiers is enforced by using different loss functions. In particular, we present a new loss function that results from the combination of Dice and Structural Similarity Index. The proposed ensemble is implemented by combining different backbone networks using the DeepLabV3+ and HarDNet environment. The proposal is evaluated through an extensive empirical evaluation on two real-world scenarios: polyp and skin segmentation. All the code is available online at https://github.com/LorisNanni.
Image-guided depth completion aims to generate dense depth maps with sparse depth measurements and corresponding RGB images. Currently, spatial propagation networks (SPNs) are the most popular affinity-based methods in depth completion, but they still suffer from the representation limitation of the fixed affinity and the over smoothing during iterations. Our solution is to estimate independent affinity matrices in each SPN iteration, but it is over-parameterized and heavy calculation. This paper introduces an efficient model that learns the affinity among neighboring pixels with an attention-based, dynamic approach. Specifically, the Dynamic Spatial Propagation Network (DySPN) we proposed makes use of a non-linear propagation model (NLPM). It decouples the neighborhood into parts regarding to different distances and recursively generates independent attention maps to refine these parts into adaptive affinity matrices. Furthermore, we adopt a diffusion suppression (DS) operation so that the model converges at an early stage to prevent over-smoothing of dense depth. Finally, in order to decrease the computational cost required, we also introduce three variations that reduce the amount of neighbors and attentions needed while still retaining similar accuracy. In practice, our method requires less iteration to match the performance of other SPNs and yields better results overall. DySPN outperforms other state-of-the-art (SoTA) methods on KITTI Depth Completion (DC) evaluation by the time of submission and is able to yield SoTA performance in NYU Depth v2 dataset as well.
Panoptic segmentation combines instance and semantic predictions, allowing the detection of "things" and "stuff" simultaneously. Effectively approaching panoptic segmentation in remotely sensed data can be auspicious in many challenging problems since it allows continuous mapping and specific target counting. Several difficulties have prevented the growth of this task in remote sensing: (a) most algorithms are designed for traditional images, (b) image labelling must encompass "things" and "stuff" classes, and (c) the annotation format is complex. Thus, aiming to solve and increase the operability of panoptic segmentation in remote sensing, this study has five objectives: (1) create a novel data preparation pipeline for panoptic segmentation, (2) propose an annotation conversion software to generate panoptic annotations; (3) propose a novel dataset on urban areas, (4) modify the Detectron2 for the task, and (5) evaluate difficulties of this task in the urban setting. We used an aerial image with a 0,24-meter spatial resolution considering 14 classes. Our pipeline considers three image inputs, and the proposed software uses point shapefiles for creating samples in the COCO format. Our study generated 3,400 samples with 512x512 pixel dimensions. We used the Panoptic-FPN with two backbones (ResNet-50 and ResNet-101), and the model evaluation considered semantic instance and panoptic metrics. We obtained 93.9, 47.7, and 64.9 for the mean IoU, box AP, and PQ. Our study presents the first effective pipeline for panoptic segmentation and an extensive database for other researchers to use and deal with other data or related problems requiring a thorough scene understanding.
We evaluated whether model explanations could efficiently detect bias in image classification by highlighting discriminating features, thereby removing the reliance on sensitive attributes for fairness calculations. To this end, we formulated important characteristics for bias detection and observed how explanations change as the degree of bias in models change. The paper identifies strengths and best practices for detecting bias using explanations, as well as three main weaknesses: explanations poorly estimate the degree of bias, could potentially introduce additional bias into the analysis, and are sometimes inefficient in terms of human effort involved.
Compressing deep networks is essential to expand their range of applications to constrained settings. The need for compression however often arises long after the model was trained, when the original data might no longer be available. On the other hand, unlabeled data, not necessarily related to the target task, is usually plentiful, especially in image classification tasks. In this work, we propose a scheme to leverage such samples to distill the knowledge learned by a large teacher network to a smaller student. The proposed technique relies on (i) preferentially sampling datapoints that appear related, and (ii) taking better advantage of the learning signal. We show that the former speeds up the student's convergence, while the latter boosts its performance, achieving performances closed to what can be expected with the original data.
Generative Neural Radiance Field (GNeRF) models, which extract implicit 3D representations from 2D images, have recently been shown to produce realistic images representing rigid objects, such as human faces or cars. However, they usually struggle to generate high-quality images representing non-rigid objects, such as the human body, which is of a great interest for many computer graphics applications. This paper proposes a 3D-aware Semantic-Guided Generative Model (3D-SGAN) for human image synthesis, which integrates a GNeRF and a texture generator. The former learns an implicit 3D representation of the human body and outputs a set of 2D semantic segmentation masks. The latter transforms these semantic masks into a real image, adding a realistic texture to the human appearance. Without requiring additional 3D information, our model can learn 3D human representations with a photo-realistic controllable generation. Our experiments on the DeepFashion dataset show that 3D-SGAN significantly outperforms the most recent baselines.
As autonomous vehicles and autonomous racing rise in popularity, so does the need for faster and more accurate detectors. While our naked eyes are able to extract contextual information almost instantly, even from far away, image resolution and computational resources limitations make detecting smaller objects (that is, objects that occupy a small pixel area in the input image) a genuinely challenging task for machines and a wide-open research field. This study explores how the popular YOLOv5 object detector can be modified to improve its performance in detecting smaller objects, with a particular application in autonomous racing. To achieve this, we investigate how replacing certain structural elements of the model (as well as their connections and other parameters) can affect performance and inference time. In doing so, we propose a series of models at different scales, which we name `YOLO-Z', and which display an improvement of up to 6.9% in mAP when detecting smaller objects at 50% IOU, at the cost of just a 3ms increase in inference time compared to the original YOLOv5. Our objective is to inform future research on the potential of adjusting a popular detector such as YOLOv5 to address specific tasks and provide insights on how specific changes can impact small object detection. Such findings, applied to the broader context of autonomous vehicles, could increase the amount of contextual information available to such systems.
The distance protection relays are used to determine the impedance based fault location according to the current and voltage magnitudes in the transmission lines. However, the fault location cannot be correctly detected in mixed transmission lines due to different characteristic impedance per unit length because the characteristic impedance of high voltage cable line is significantly different from overhead line. Thus, determinations of the fault section and location with the distance protection relays are difficult in the mixed transmission lines. In this study, 154 kV overhead transmission line and underground cable line are examined as the mixed transmission line for the distance protection relays. Phase to ground faults are created in the mixed transmission line. overhead line section and underground cable section are simulated by using PSCAD-EMTDC.The short circuit fault images are generated in the distance protection relay for the overhead transmission line and underground cable transmission line faults. The images include the R-X impedance diagram of the fault, and the R-X impedance diagram have been detected by applying image processing steps. Artificial neural network (ANN) and the regression methods are used for prediction of the fault location, and the results of image processing are used as the input parameters for the training process of ANN and the regression methods. The results of ANN and regression methods are compared to select the most suitable method at the end of this study for forecasting of the fault location in transmission lines.
The recent surge in the adoption of machine learning techniques for materials design, discovery, and characterization has resulted in an increased interest and application of Image Driven Machine Learning (IDML) approaches. In this work, we review the application of IDML to the field of materials characterization. A hierarchy of six action steps is defined which compartmentalizes a problem statement into well-defined modules. The studies reviewed in this work are analyzed through the decisions adopted by them at each of these steps. Such a review permits a granular assessment of the field, for example the impact of IDML on materials characterization at the nanoscale, the number of images in a typical dataset required to train a semantic segmentation model on electron microscopy images, the prevalence of transfer learning in the domain, etc. Finally, we discuss the importance of interpretability and explainability, and provide an overview of two emerging techniques in the field: semantic segmentation and generative adversarial networks.
Handwritten document images can be highly affected by degradation for different reasons: Paper ageing, daily-life scenarios (wrinkles, dust, etc.), bad scanning process and so on. These artifacts raise many readability issues for current Handwritten Text Recognition (HTR) algorithms and severely devalue their efficiency. In this paper, we propose an end to end architecture based on Generative Adversarial Networks (GANs) to recover the degraded documents into a clean and readable form. Unlike the most well-known document binarization methods, which try to improve the visual quality of the degraded document, the proposed architecture integrates a handwritten text recognizer that promotes the generated document image to be more readable. To the best of our knowledge, this is the first work to use the text information while binarizing handwritten documents. Extensive experiments conducted on degraded Arabic and Latin handwritten documents demonstrate the usefulness of integrating the recognizer within the GAN architecture, which improves both the visual quality and the readability of the degraded document images. Moreover, we outperform the state of the art in H-DIBCO 2018 challenge, after fine tuning our pre-trained model with synthetically degraded Latin handwritten images, on this task.