Lightweight Deep Exemplar Colorization via Semantic Attention-Guided Laplacian Pyramid.

Exemplar-based colorization aims to generate plausible colors for a grayscale image with the guidance of a color reference image. The main challenging problem is finding the correct semantic correspondence between the target image and the reference image. However, the colors of the object and background are often confused in the existing methods. Besides, these methods usually use simple encoder-decoder architectures or pyramid structures to extract features and lack appropriate fusion mechanisms, which results in the loss of high-frequency information or high complexity. To address these problems, this paper proposes a lightweight semantic attention-guided Laplacian pyramid network (SAGLP-Net) for deep exemplar-based colorization, exploiting the inherent multi-scale properties of color representations. They are exploited through a Laplacian pyramid, and semantic information is introduced as high-level guidance to align the object and background information. Specially, a semantic guided non-local attention fusion module is designed to exploit the long-range dependency and fuse the local and global features. Moreover, a Laplacian pyramid fusion module based on criss-cross attention is proposed to fuse high frequency components in the large-scale domain. An unsupervised multi-scale multi-loss training strategy is further introduced for network training, which combines pixel loss, color histogram loss, total variance regularisation, and adversarial loss. Experimental results demonstrate that our colorization method achieves better subjective and objective performance with lower complexity than the state-of-the-art methods.

Improving the perception of low-light enhanced images.

Improving images captured under low-light conditions has become an important topic in computational color imaging, as it has a wide range of applications. Most current methods are either based on handcrafted features or on end-to-end training of deep neural networks that mostly focus on minimizing some distortion metric -such as PSNR or SSIM- on a set of training images. However, the minimization of distortion metrics does not mean that the results are optimal in terms of perception (i.e. perceptual quality). As an example, the perception-distortion trade-off states that, close to the optimal results, improving distortion results in worsening perception. This means that current low-light image enhancement methods -that focus on distortion minimization- cannot be optimal in the sense of obtaining a good image in terms of perception errors. In this paper, we propose a post-processing approach in which, given the original low-light image and the result of a specific method, we are able to obtain a result that resembles as much as possible that of the original method, but, at the same time, giving an improvement in the perception of the final image. More in detail, our method follows the hypothesis that in order to minimally modify the perception of an input image, any modification should be a combination of a local change in the shading across a scene and a global change in illumination color. We demonstrate the ability of our method quantitatively using perceptual blind image metrics such as BRISQUE, NIQE, or UNIQUE, and through user preference tests.

Trust Your Good Friends: Source-Free Domain Adaptation by Reciprocal Neighborhood Clustering.

Domain adaptation (DA) aims to alleviate the domain shift between source domain and target domain. Most DA methods require access to the source data, but often that is not possible (e.g., due to data privacy or intellectual property). In this paper, we address the challenging source-free domain adaptation (SFDA) problem, where the source pretrained model is adapted to the target domain in the absence of source data. Our method is based on the observation that target data, which might not align with the source domain classifier, still forms clear clusters. We capture this intrinsic structure by defining local affinity of the target data, and encourage label consistency among data with high local affinity. We observe that higher affinity should be assigned to reciprocal neighbors. To aggregate information with more context, we consider expanded neighborhoods with small affinity values. Furthermore, we consider the density around each target sample, which can alleviate the negative impact of potential outliers. In the experimental results we verify that the inherent structure of the target features is an important source of information for domain adaptation. We demonstrate that this local structure can be efficiently captured by considering the local neighbors, the reciprocal neighbors, and the expanded neighborhood. Finally, we achieve state-of-the-art performance on several 2D image and 3D point cloud recognition datasets.

Distributed Learning and Inference With Compressed Images.

Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are increasingly common (e.g. autonomous vehicles, cloud computing, smartphones). In addition, many devices suffer from limited resources to store or transmit data (e.g. storage space, channel capacity). In these scenarios, lossy image compression plays a crucial role to effectively increase the number of images collected under such constraints. However, lossy compression entails some undesired degradation of the data that may harm the performance of the downstream analysis task at hand, since important semantic information may be lost in the process. Moreover, we may only have compressed images at training time but are able to use original images at inference time (i.e. test), or vice versa, and in such a case, the downstream model suffers from covariate shift. In this paper, we analyze this phenomenon, with a special focus on vision-based perception for autonomous driving as a paradigmatic scenario. We see that loss of semantic information and covariate shift do indeed exist, resulting in a drop in performance that depends on the compression rate. In order to address the problem, we propose dataset restoration, based on image restoration with generative adversarial networks (GANs). Our method is agnostic to both the particular image compression method and the downstream task; and has the advantage of not adding additional cost to the deployed models, which is particularly important in resource-limited devices. The presented experiments focus on semantic segmentation as a challenging use case, cover a broad range of compression rates and diverse datasets, and show how our method is able to significantly alleviate the negative effects of compression on the downstream visual task.

Learning Effective RGB-D Representations for Scene Recognition.

Deep convolutional networks (CNN) can achieve impressive results on RGB scene recognition thanks to large datasets such as Places. In contrast, RGB-D scene recognition is still underdeveloped in comparison, due to two limitations of RGB-D data we address in this paper. The first limitation is the lack of depth data for training deep learning models. Rather than fine tuning or transferring RGB-specific features, we address this limitation by proposing an architecture and a twostep training approach that directly learns effective depth-specific features using weak supervision via patches. The resulting RGBD model also benefits from more complementary multimodal features. Another limitation is the short range of depth sensors (typically 0.5m to 5.5m), resulting in depth images not capturing distant objects in the scenes that RGB images can. We show that this limitation can be addressed by using RGB-D videos, where more comprehensive depth information is accumulated as the camera travels across the scenes. Focusing on this scenario, we introduce the ISIA RGB-D video dataset to evaluate RGB-D scene recognition with videos. Our video recognition architecture combines convolutional and recurrent neural networks (RNNs) that are trained in three steps with increasingly complex data to learn effective features (i.e. patches, frames and sequences). Our approach obtains state-of-the-art performances on RGB-D image (NYUD2 and SUN RGB-D) and video (ISIA RGB-D) scene recognition.

Multi-Scale Multi-Feature Context Modeling for Scene Recognition in the Semantic Manifold.

Before the big data era, scene recognition was often approached with two-step inference using localized intermediate representations (objects, topics, and so on). One of such approaches is the semantic manifold (SM), in which patches and images are modeled as points in a semantic probability simplex. Patch models are learned resorting to weak supervision via image labels, which leads to the problem of scene categories co-occurring in this semantic space. Fortunately, each category has its own co-occurrence patterns that are consistent across the images in that category. Thus, discovering and modeling these patterns are critical to improve the recognition performance in this representation. Since the emergence of large data sets, such as ImageNet and Places, these approaches have been relegated in favor of the much more powerful convolutional neural networks (CNNs), which can automatically learn multi-layered representations from the data. In this paper, we address many limitations of the original SM approach and related works. We propose discriminative patch representations using neural networks and further propose a hybrid architecture in which the semantic manifold is built on top of multiscale CNNs. Both representations can be computed significantly faster than the Gaussian mixture models of the original SM. To combine multiple scales, spatial relations, and multiple features, we formulate rich context models using Markov random fields. To solve the optimization problem, we analyze global and local approaches, where a top-down hierarchical algorithm has the best performance. Experimental results show that exploiting different types of contextual relations jointly consistently improves the recognition accuracy.

Predictive value of PAK6 and PSMB4 expression in patients with localized prostate cancer treated with dose-escalation radiation therapy and androgen deprivation therapy.

PURPOSE: The present study analyzed the expression by immunochemistry of the novel markers P21-activated protein kinase 6 (PAK6) and proteasome beta-4 subunit (PSMB4) in men with localized prostate cancer (PC) who were treated with dose-escalation radiotherapy (RT) and androgen deprivation therapy. MATERIALS AND METHODS: Between 1996 and 2004, a cohort of 129 patients with PC who underwent diagnostic biopsies pretreatment and 24 to 36 months following RT were enrolled in this study. Suitable archival diagnostic tissue was obtained from 89 patients. Median follow-up was 129 months (48-198). Correlation analysis was done to assess association between PAK6 and PSMB4 expression and clinical outcome. RESULTS: PAK6 and PSMB4 were expressed in the cytoplasm in 62% and 96.7% of diagnostic biopsies, respectively. Increased staining for PAK6 was significantly (P = 0.04) correlated with higher Gleason scores. In the multivariate analysis, the intensity of PSMB4 staining was an independent predictor of local relapse (hazard ratio = 8.6, P = 0.04). CONCLUSIONS: To our knowledge, this is the first description of PAK6 and PSMB4 expression in the diagnostic specimens of men with PC who were treated with RT. If confirmed by further studies, increased expression of these genes could be used to identify patients at a high risk of developing local failure following high-dose RT, thus better tailoring treatments for the individual patient.

Transdermal iontophoresis with verapamil and dexamethasone in the acute phase of peyronie's disease. Our experience.

OBJECTIVES: To evaluate the treatment of Peyronie's disease (PD) with verapamil and dexamethasone iontophoresis. METHODS: Twenty nine patients with PD were treated by means of a Miniphysionize" dispositive 3 sessions a week during 4 consecutive weeks. 5mL of a combination of verapamil(10mg.) and dexamethasone (4mg.) were transdermally administered with a 2.5 mA current during 20 min. The aim is to evaluate treatment efficacy in correcting penile curvature (Kelami test), plaque size (penis ultrasound (US)) improvement of pain and, other parameters like erectile function (EF), intercourse capacity or adverse effects of the treatment, which were evaluated with questionnaires. RESULTS: All patients completed the treatment protocol (12 sessions) and a total number of 348 sessions of iontophoresis were performed. After treatment, 3 patients (10.7%) continued with pain, but it disappeared in 25 of them (89.3%). A decrease of the size of the plaque was observed in 13 patients (44.8%), even disappearance in 4 patients (13.8%). No patient had curvature decrease after treatment. However, EF (IIEF score) and ability for intercourse improved in 3 (10.3%) and 4 patients (13.8%) respectively. CONCLUSION: Verapamil and dexamethasone iontophoresis is a safe and reliable treatment resolving painful erections in the acute phase of PD. However its efficacy in solving penile curvature and erectile dysfunction (ED) is more limited.

Iontoforesis transdérmica con verapamilo y dexametasona para la fase aguda de la Enfermedad de La Peyronie. Nuestra experiencia / Transdermal iontophoresis with verapamil and dexamethasone in the acute phase of peyronie's disease. Our experience

OBJETIVO: Evaluar el resultado del tratamiento de la Enfermedad de Peyronie (EP) mediante iontoforesis de verapamilo y dexametasona. MÉTODOS: Tratamiento de 29 pacientes con EP en 3 sesiones semanales durante cuatro semanas consecutivas mediante un dispositivo Miniphysionizer©. Administrando 5 mL de una combinación de 10mg de verapamilo y 4mg de dexametasona, aplicado transdérmico a través de una corriente de 2.5 mA durante ciclos de 20 min. Se evalúa la eficacia del tratamiento mediante corrección de curvatura peneana (test de Kelami), tamaño de la placa (ecografía peneana), mejoría del dolor y otros parámetros, como, la función eréctil, capacidad de penetración o efectos secundarios del tratamiento, que fueron valorados mediante cuestionarios. RESULTADO: Todos los pacientes completaron el protocolo de tratamiento (12 sesiones) y se efectuaron un total de 348 sesiones de iontoforesis. Tras finalizar el tratamiento completo, 3 pacientes (10.7%) continuaron presentando dolor, mientras que remitió en 25 de ellos (89.3%). En 13 pacientes (44.8%) se observó una disminución del tamaño de la placa, desapareciendo incluso totalmente en 4 pacientes (13.8%). La curvatura no se disminuyó en ninguno de los pacientes tras el tratamiento. Sin embargo, la función eréctil mejoró en 3 pacientes (10.3%) según la puntuación del IIEF, y la capacidad para la penetración mejoró en 4 pacientes (13.8%). CONCLUSIONES: La iontoforesis con verapamilo y dexametasona es un tratamiento seguro y eficaz en la resolución del dolor con las erecciones en la fase aguda de la EP. Sin embargo la eficacia en la resolución de la curvatura y la DE es más limitado (AU)

OBJECTIVES: To evaluate the treatment of Peyronie's disease (PD) with verapamil and dexamethasone iontophoresis. METHODS: Twenty nine patients with PD were treated by means of a Miniphysionizer” dispositive 3 sessions a week during 4 consecutive weeks. 5mL of a combination of verapamil (10mg.) and dexamethasone (4mg.) were transdermally administered with a 2.5 mA current during 20 min. The aim is to evaluate treatment efficacy in correcting penile curvature (Kelami test), plaque size (penis ultrasound (US)) improvement of pain and, other parameters like erectile function (EF), intercourse capacity or adverse effects of the treatment, which were evaluated with questionnaires. RESULTS: All patients completed the treatment protocol (12 sessions) and a total number of 348 sessions of iontophoresis were performed. After treatment, 3 patients (10.7%) continued with pain, but it disappeared in 25 of them (89.3%). A decrease of the size of the plaque was observed in 13 patients (44.8%), even disappearance in 4 patients (13.8%). No patient had curvature decrease after treatment. However, EF (IIEF score) and ability for intercourse improved in 3 (10.3%) and 4 patients (13.8%) respectively. CONCLUSION: Verapamil and dexamethasone iontophoresis is a safe and reliable treatment resolving painful erections in the acute phase of PD. However its efficacy in solving penile curvature and erectile dysfunction (ED) is more limited (AU)