RESUMEN
Previous studies of age-related macular degeneration (AMD) report impaired facial expression recognition even with enlarged face images. Here, we test potential benefits of caricaturing (exaggerating how the expression's shape differs from neutral) as an image enhancement procedure targeted at mid- to high-level cortical vision. Experiment 1 provides proof-of-concept using normal vision observers shown blurred images as a partial simulation of AMD. Caricaturing significantly improved expression recognition (happy, sad, anger, disgust, fear, surprise) by â¼4%-5% across young adults and older adults (mean age 73 years); two different severities of blur; high, medium, and low intensity of the original expression; and all intermediate accuracy levels (impaired but still above chance). Experiment 2 tested AMD patients, running 19 eyes monocularly (from 12 patients, 67-94 years) covering a wide range of vision loss (acuities 6/7.5 to poorer than 6/360). With faces pre-enlarged, recognition approached ceiling and was only slightly worse than matched controls for high- and medium-intensity expressions. For low-intensity expressions, recognition of veridical expressions remained impaired and was significantly improved with caricaturing across all levels of vision loss by 5.8%. Overall, caricaturing benefits emerged when improvement was most needed, that is, when initial recognition of uncaricatured expressions was impaired.
Asunto(s)
Emociones/fisiología , Reconocimiento Facial/fisiología , Degeneración Macular/fisiopatología , Reconocimiento Visual de Modelos/fisiología , Adulto , Anciano , Anciano de 80 o más Años , Expresión Facial , Femenino , Humanos , Masculino , Persona de Mediana Edad , Adulto JovenRESUMEN
Tactile vision substitution devices present visual images as tactile representations on the skin. In this study we have tested the performance of a prototype 96-tactor vibrotactile using a subset of 64 tactors. We have determined the tactile spatial acuity and intensity discrimination in 14 naïve subjects. Spatial acuity was determined using a grating acuity task. Subjects could successfully identify the orientation of horizontal and vertical gratings with an average psychophysical threshold of 120 mm. When diagonal gratings were included in the analysis, the median performance dropped below psychophysical threshold, but was still significantly above chance at gratings of 142 mm wide. Intensity discrimination yielded an average Weber fraction of 0.44, corresponding to 13 discernable "gray levels" in the available dynamic range. Interleaved stimulation of the motors did not significantly affect spatial acuity or intensity discrimination.
Asunto(s)
Auxiliares Sensoriales , Detección de Señal Psicológica , Tacto , Adulto , Femenino , Humanos , Masculino , Vibración , Adulto JovenRESUMEN
Tactile vision substitution devices are assistive technologies for the blind that redirect visual information to the tactile sense. They typically include a tactile display that conveys visual information to the skin. Two important parameters that determine the maximum information bandwidth of tactile displays are the spatial acuity of the skin, and the ability of the user to discriminate between stimulus intensities. These two parameters were investigated by determining the two-point discrimination (TPD) threshold and the just-noticeable intensity difference (JND) using coin motors on the lower back. Coin motors are eccentric rotating-mass motors that are affordable, energy-efficient, and easy to implement. The lower back was chosen because it is a discreet place to wear assistive technology. It is generally available for use, as it is usually not critically involved in activities of daily living. Rehabilitation with sensory substitution devices often requires training by professional occupational therapists, because the user needs to extract visual information from sparse information presented through an alternative channel such as the skin. In this study they determined whether short, automated training sessions of 5 min each could improve the TPD threshold and JND. It was found that 10 min of computer-assisted training improved the vibrotactile TPD threshold on the lower back by 36%, and that 18 min of training improved the just-noticeable intensity difference (JND) by 44%. It was concluded that short, automated training sessions could provide a fast and inexpensive means to improve people's basic spatial acuity and intensity discrimination skills with coin motors.
Asunto(s)
Discriminación en Psicología , Estimulación Física/instrumentación , Umbral Sensorial , Fenómenos Fisiológicos de la Piel , Piel/inervación , Percepción Espacial , Percepción del Tacto , Vibración , Adulto , Diseño de Equipo , Femenino , Humanos , Región Lumbosacra , Masculino , Persona de Mediana Edad , Estimulación Física/métodos , Detección de Señal Psicológica , Adulto JovenRESUMEN
We have tested the potential of three types of vibration motors for use in a tactile vision substitution device for the blind. The motors were of the coin type, which are available off-the-shelf, and are characterized by their affordability, energy efficiency, and ease of implementation. The primary limitation of coin motors is the lack of control they offer over stimulus parameters. Specifically, adjusting the input voltage of a coin motor not only changes the vibration intensity, but also the vibration frequency and duration. This characteristic may result in unpredictable perceptions in psychophysical tests. By using standard psychophysical procedures, we were able to show that the tested coin motors evoked predictable magnitude perceptions across their dynamic range, following Fechner's law as if vibration intensity alone were varied. The best-performing motor was able to generate a median number of 15 available just-noticeable differences, meaning that it was potentially capable of conveying 16 gray levels in its dynamic range. We conclude that coin motors are potential candidates for the construction of a tactile display to substitute for lost vision.
Asunto(s)
Ceguera , Tacto/fisiología , Vibración , Personas con Daño Visual , Adulto , Femenino , Humanos , Masculino , Persona de Mediana Edad , Adulto JovenRESUMEN
Damage to central vision, of which age-related macular degeneration (AMD) is the most common cause, leaves patients with only blurred peripheral vision. Previous approaches to improving face recognition in AMD have employed image manipulations designed to enhance early-stage visual processing (e.g., magnification, increased HSF contrast). Here, we argue that further improvement may be possible by targeting known properties of mid- and/or high-level face processing. We enhance identity-related shape information in the face by caricaturing each individual away from an average face. We simulate early- through late-stage AMD-blur by filtering spatial frequencies to mimic the amount of blurring perceived at approximately 10° through 30° into the periphery (assuming a face seen premagnified on a tablet computer). We report caricature advantages for all blur levels, for face viewpoints from front view to semiprofile, and in tasks involving perceiving differences in facial identity between pairs of people, remembering previously learned faces, and rejecting new faces as unknown. Results provide a proof of concept that caricaturing may assist in improving face recognition in AMD and other disorders of central vision.
Asunto(s)
Cara , Degeneración Macular/rehabilitación , Modelos Teóricos , Reconocimiento Visual de Modelos/fisiología , Adolescente , Adulto , Femenino , Humanos , Degeneración Macular/fisiopatología , Masculino , Estimulación Luminosa/métodos , Adulto JovenRESUMEN
Unsupervised object discovery (UOD) refers to the task of discriminating the whole region of objects from the background within a scene without relying on labeled datasets, which benefits the task of bounding-box-level localization and pixel-level segmentation. This task is promising due to its ability to discover objects in a generic manner. We roughly categorize existing techniques into two main directions, namely the generative solutions based on image resynthesis, and the clustering methods based on self-supervised models. We have observed that the former heavily relies on the quality of image reconstruction, while the latter shows limitations in effectively modeling semantic correlations. To directly target at object discovery, we focus on the latter approach and propose a novel solution by incorporating weakly-supervised contrastive learning (WCL) to enhance semantic information exploration. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images, which is achieved by fine-tuning the feature encoder of a self-supervised model, namely DINO, via WCL. Subsequently, we introduce Principal Component Analysis (PCA) to localize object regions. The principal projection direction, corresponding to the maximal eigenvalue, serves as an indicator of the object region(s). Extensive experiments on benchmark unsupervised object discovery datasets demonstrate the effectiveness of our proposed solution. The source code and experimental results are publicly available via our project page at https://github.com/npucvr/WSCUOD.git.
RESUMEN
With the help of the deep learning paradigm, many point cloud networks have been invented for visual analysis. However, there is great potential for development of these networks since the given information of point cloud data has not been fully exploited. To improve the effectiveness of existing networks in analyzing point cloud data, we propose a plug-and-play module, PnP-3D, aiming to refine the fundamental point cloud feature representations by involving more local context and global bilinear response from explicit 3D space and implicit feature space. To thoroughly evaluate our approach, we conduct experiments on three standard point cloud analysis tasks, including classification, semantic segmentation, and object detection, where we select three state-of-the-art networks from each task for evaluation. Serving as a plug-and-play module, PnP-3D can significantly boost the performances of established networks. In addition to achieving state-of-the-art results on four widely used point cloud benchmarks, we present comprehensive ablation studies and visualizations to demonstrate our approach's advantages. The code will be available at https://github.com/ShiQiu0419/pnp-3d.
RESUMEN
We propose a novel generative saliency prediction framework that adopts an informative energy-based model as a prior distribution. The energy-based prior model is defined on the latent space of a saliency generator network that generates the saliency map based on a continuous latent variables and an observed image. Both the parameters of saliency generator and the energy-based prior are jointly trained via Markov chain Monte Carlo-based maximum likelihood estimation, in which the sampling from the intractable posterior and prior distributions of the latent variables are performed by Langevin dynamics. With the generative saliency model, we can obtain a pixel-wise uncertainty map from an image, indicating model confidence in the saliency prediction. Different from existing generative models, which define the prior distribution of the latent variables as a simple isotropic Gaussian distribution, our model uses an energy-based informative prior which can be more expressive in capturing the latent space of the data. With the informative energy-based prior, we extend the Gaussian distribution assumption of generative models to achieve a more representative distribution of the latent space, leading to more reliable uncertainty estimation. We apply the proposed frameworks to both RGB and RGB-D salient object detection tasks with both transformer and convolutional neural network backbones. We further propose an adversarial learning algorithm and a variational inference algorithm as alternatives to train the proposed generative framework. Experimental results show that our generative saliency model with an energy-based prior can achieve not only accurate saliency predictions but also reliable uncertainty maps that are consistent with human perception.
RESUMEN
Vision transformers have shown great success on numerous computer vision tasks. However, their central component, softmax attention, prohibits vision transformers from scaling up to high-resolution images, due to both the computational complexity and memory footprint being quadratic. Linear attention was introduced in natural language processing (NLP) which reorders the self-attention mechanism to mitigate a similar issue, but directly applying existing linear attention to vision may not lead to satisfactory results. We investigate this problem and point out that existing linear attention methods ignore an inductive bias in vision tasks, i.e., 2D locality. In this article, we propose Vicinity Attention, which is a type of linear attention that integrates 2D locality. Specifically, for each image patch, we adjust its attention weight based on its 2D Manhattan distance from its neighbouring patches. In this case, we achieve 2D locality in a linear complexity where the neighbouring image patches receive stronger attention than far away patches. In addition, we propose a novel Vicinity Attention Block that is comprised of Feature Reduction Attention (FRA) and Feature Preserving Connection (FPC) in order to address the computational bottleneck of linear attention approaches, including our Vicinity Attention, whose complexity grows quadratically with respect to the feature dimension. The Vicinity Attention Block computes attention in a compressed feature space with an extra skip connection to retrieve the original feature distribution. We experimentally validate that the block further reduces computation without degenerating the accuracy. Finally, to validate the proposed methods, we build a linear vision transformer backbone named Vicinity Vision Transformer (VVT). Targeting general vision tasks, we build VVT in a pyramid structure with progressively reduced sequence length. We perform extensive experiments on CIFAR-100, ImageNet-1 k, and ADE20 K datasets to validate the effectiveness of our method. Our method has a slower growth rate in terms of computational overhead than previous transformer-based and convolution-based networks when the input resolution increases. In particular, our approach achieves state-of-the-art image classification accuracy with 50% fewer parameters than previous approaches.
RESUMEN
Purpose: Accurate mapping of phosphene locations from visual prostheses is vital to encode spatial information. This process may involve the subject pointing to evoked phosphene locations with their finger. Here, we demonstrate phosphene mapping for a retinal implant using eye movements and compare it with retinotopic electrode positions and previous results using conventional finger-based mapping. Methods: Three suprachoroidal retinal implant recipients (NCT03406416) indicated the spatial position of phosphenes. Electrodes were stimulated individually, and the subjects moved their finger (finger based) or their eyes (gaze based) to the perceived phosphene location. The distortion of the measured phosphene locations from the expected locations (retinotopic electrode locations) was characterized with Procrustes analysis. Results: The finger-based phosphene locations were compressed spatially relative to the expected locations all three subjects, but preserved the general retinotopic arrangement (scale factors ranged from 0.37 to 0.83). In two subjects, the gaze-based phosphene locations were similar to the expected locations (scale factors of 0.72 and 0.99). For the third subject, there was no apparent relationship between gaze-based phosphene locations and electrode locations (scale factor of 0.07). Conclusions: Gaze-based phosphene mapping was achievable in two of three tested retinal prosthesis subjects and their derived phosphene maps correlated well with the retinotopic electrode layout. A third subject could not produce a coherent gaze-based phosphene map, but this may have revealed that their phosphenes were indistinct spatially. Translational Relevance: Gaze-based phosphene mapping is a viable alternative to conventional finger-based mapping, but may not be suitable for all subjects.
Asunto(s)
Movimientos Oculares , Prótesis Visuales , Humanos , Fosfenos , Trastornos de la Visión , Retina/cirugíaRESUMEN
Super-Resolution convolutional neural networks have recently demonstrated high-quality restoration for single images. However, existing algorithms often require very deep architectures and long training times. Furthermore, current convolutional neural networks for super-resolution are unable to exploit features at multiple scales and weigh them equally or at only static scale only, limiting their learning capability. In this exposition, we present a compact and accurate super-resolution algorithm, namely, densely residual laplacian network (DRLN). The proposed network employs cascading residual on the residual structure to allow the flow of low-frequency information to focus on learning high and mid-level features. In addition, deep supervision is achieved via the densely concatenated residual blocks settings, which also helps in learning from high-level complex features. Moreover, we propose Laplacian attention to model the crucial features to learn the inter and intra-level dependencies between the feature maps. Furthermore, comprehensive quantitative and qualitative evaluations on low-resolution, noisy low-resolution, and real historical image benchmark datasets illustrate that our DRLN algorithm performs favorably against the state-of-the-art methods visually and accurately.
RESUMEN
Conventional object detection models require large amounts of training data. In comparison, humans can recognize previously unseen objects by merely knowing their semantic description. To mimic similar behavior, zero-shot object detection (ZSD) aims to recognize and localize "unseen" object instances by using only their semantic information. The model is first trained to learn the relationships between visual and semantic domains for seen objects, later transferring the acquired knowledge to totally unseen objects. This setting gives rise to the need for correct alignment between visual and semantic concepts so that the unseen objects can be identified using only their semantic attributes. In this article, we propose a novel loss function called "polarity loss" that promotes correct visual-semantic alignment for an improved ZSD. On the one hand, it refines the noisy semantic embeddings via metric learning on a "semantic vocabulary" of related concepts to establish a better synergy between visual and semantic domains. On the other hand, it explicitly maximizes the gap between positive and negative predictions to achieve better discrimination between seen, unseen, and background objects. Our approach is inspired by embodiment theories in cognitive science that claim human semantic understanding to be grounded in past experiences (seen objects), related linguistic concepts (word vocabulary), and visual perception (seen/unseen object images). We conduct extensive evaluations on the Microsoft Common Objects in Context (MS-COCO) and Pascal Visual Object Classes (VOC) datasets, showing significant improvements over state of the art. Our code and evaluation protocols available at: https://github.com/salman-h-khan/PL-ZSD_Release.
RESUMEN
We propose the first stochastic framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection models treat this task as a point estimation problem by predicting a single saliency map following a deterministic learning pipeline. We argue that, however, the deterministic solution is relatively ill-posed. Inspired by the saliency data labeling process, we propose a generative architecture to achieve probabilistic RGB-D saliency detection which utilizes a latent variable to model the labeling variations. Our framework includes two main models: 1) a generator model, which maps the input image and latent variable to stochastic saliency prediction, and 2) an inference model, which gradually updates the latent variable by sampling it from the true or approximate posterior distribution. The generator model is an encoder-decoder saliency network. To infer the latent variable, we introduce two different solutions: i) a Conditional Variational Auto-encoder with an extra encoder to approximate the posterior distribution of the latent variable; and ii) an Alternating Back-Propagation technique, which directly samples the latent variable from the true posterior distribution. Qualitative and quantitative results on six challenging RGB-D benchmark datasets show our approach's superior performance in learning the distribution of saliency maps. The source code is publicly available via our project page: https://github.com/JingZhang617/UCNet.
RESUMEN
In the crystal structure of the title compound, 2C(22)H(24)P(+)·I(8)(2-), the I(8)(2-) anion is located on a crystallographic inversion centre and consists of two tri-iodide anions linked by di-iodine at angles of 89.92 4)° to form a planar `Z'-shaped dianion. The octaiodides are linked via long-range interactions [3.877 11) ] into infinite polyiodide ribbons. This is the first example of a structure containing an [(o-tolyl)(3)PMe](+) cation, and the C(Me)-P-C-C(Me) torsion angles of -54.0 11), -51.3 11) and -48.2 11)° indicate that the configuration is exo(3).
RESUMEN
Deep convolutional neural networks perform better on images containing spatially invariant degradations, also known as synthetic degradations; however, their performance is limited on real-degraded photographs and requires multiple-stage network modeling. To advance the practicability of restoration algorithms, this article proposes a novel single-stage blind real image restoration network (R²Net) by employing a modular architecture. We use a residual on the residual structure to ease low-frequency information flow and apply feature attention to exploit the channel dependencies. Furthermore, the evaluation in terms of quantitative metrics and visual quality for four restoration tasks, i.e., denoising, super-resolution, raindrop removal, and JPEG compression on 11 real degraded datasets against more than 30 state-of-the-art algorithms, demonstrates the superiority of our R²Net. We also present the comparison on three synthetically generated degraded datasets for denoising to showcase our method's capability on synthetics denoising. The codes, trained models, and results are available on https://github.com/saeed-anwar/R2Net.
RESUMEN
The advances made in predicting visual saliency using deep neural networks come at the expense of collecting large-scale annotated data. However, pixel-wise annotation is labor-intensive and overwhelming. In this paper, we propose to learn saliency prediction from a single noisy labelling, which is easy to obtain (e.g., from imperfect human annotation or from unsupervised saliency prediction methods). With this goal, we address a natural question: Can we learn saliency prediction while identifying clean labels in a unified framework? To answer this question, we call on the theory of robust model fitting and formulate deep saliency prediction from a single noisy labelling as robust network learning and exploit model consistency across iterations to identify inliers and outliers (i.e., noisy labels). Extensive experiments on different benchmark datasets demonstrate the superiority of our proposed framework, which can learn comparable saliency prediction with state-of-the-art fully supervised saliency methods. Furthermore, we show that simply by treating ground truth annotations as noisy labelling, our framework achieves tangible improvements over state-of-the-art methods.
RESUMEN
Purpose: To report the initial safety and efficacy results of a second-generation (44-channel) suprachoroidal retinal prosthesis at 56 weeks after device activation. Methods: Four subjects, with advanced retinitis pigmentosa and bare-light perception only, enrolled in a phase II trial (NCT03406416). A 44-channel electrode array was implanted in a suprachoroidal pocket. Device stability, efficacy, and adverse events were investigated at 12-week intervals. Results: All four subjects were implanted successfully and there were no device-related serious adverse events. Color fundus photography indicated a mild postoperative subretinal hemorrhage in two recipients, which cleared spontaneously within 2 weeks. Optical coherence tomography confirmed device stability and position under the macula. Screen-based localization accuracy was significantly better for all subjects with device on versus device off. Two subjects were significantly better with the device on in a motion discrimination task at 7, 15, and 30°/s and in a spatial discrimination task at 0.033 cycles per degree. All subjects were more accurate with the device on than device off at walking toward a target on a modified door task, localizing and touching tabletop objects, and detecting obstacles in an obstacle avoidance task. A positive effect of the implant on subjects' daily lives was confirmed by an orientation and mobility assessor and subject self-report. Conclusions: These interim study data demonstrate that the suprachoroidal prosthesis is safe and provides significant improvements in functional vision, activities of daily living, and observer-rated quality of life. Translational Relevance: A suprachoroidal prosthesis can provide clinically useful artificial vision while maintaining a safe surgical profile.
Asunto(s)
Retinitis Pigmentosa , Prótesis Visuales , Actividades Cotidianas , Humanos , Calidad de Vida , Visión OcularRESUMEN
Purpose: In a clinical trial (NCT03406416) of a second-generation (44-channel) suprachoroidal retinal prosthesis implanted in subjects with late-stage retinitis pigmentosa (RP), we assessed performance in real-world functional visual tasks and emotional well-being. Methods: The Functional Low-Vision Observer Rated Assessment (FLORA) and Impact of Vision Impairment-Very Low Vision (IVI-VLV) instruments were administered to four subjects before implantation and after device fitting. The FLORA contains 13 self-reported and 35 observer-reported items ranked for ease of conducting task (impossible-easy, central tendency given as mode). The IVI-VLV instrument quantified the impact of low vision on daily activities and emotional well-being. Results: Three subjects completed the FLORA for two years after device fitting; the fourth subject ceased participation in the FLORA after fitting for reasons unrelated to the device. For all subjects at each post-fitting visit, the mode ease of task with device ON was better or equal to device OFF. Ease of task improved over the first six months with device ON, then remained stable. Subjects reported improvements in mobility, functional vision, and quality of life with device ON. The IVI-VLV suggested self-assessed vision-related quality of life was not impacted by device implantation or usage. Conclusions: Subjects demonstrated sustained improved ease of task scores with device ON compared to OFF, indicating the device has a positive impact in the real-world setting. Translational Relevance: Our suprachoroidal retinal prosthesis shows potential utility in everyday life, by enabling an increased environmental awareness and improving access to sensory information for people with end-stage RP.
Asunto(s)
Retinitis Pigmentosa , Baja Visión , Prótesis Visuales , Humanos , Calidad de Vida , Retinitis Pigmentosa/cirugía , Visión OcularRESUMEN
Retinal prostheses are designed to restore a basic sense of sight to people with profound vision loss. They require a relatively intact posterior visual pathway (optic nerve, lateral geniculate nucleus and visual cortex). Retinal implants are options for people with severe stages of retinal degenerative disease such as retinitis pigmentosa and age-related macular degeneration. There have now been three regulatory-approved retinal prostheses. Over five hundred patients have been implanted globally over the past 15 years. Devices generally provide an improved ability to localize high-contrast objects, navigate, and perform basic orientation tasks. Adverse events have included conjunctival erosion, retinal detachment, loss of light perception, and the need for revision surgery, but are rare. There are also specific device risks, including overstimulation (which could cause damage to the retina) or delamination of implanted components, but these are very unlikely. Current challenges include how to improve visual acuity, enlarge the field-of-view, and reduce a complex visual scene to its most salient components through image processing. This review encompasses the work of over 40 individual research groups who have built devices, developed stimulation strategies, or investigated the basic physiology underpinning retinal prostheses. Current technologies are summarized, along with future challenges that face the field.