Visual Recognition Tasks Research Articles

Oculomotor changes following learned use of an eccentric retinal locus

People with bilateral central vision loss sometimes develop a new point of oculomotor reference called a preferred retinal locus (PRL) that is used for fixating and planning saccadic eye movements. How individuals develop and learn to effectively use a PRL is still debated; in particular, the time course of learning to plan saccades using a PRL and learning to stabilize peripheral fixation at the desired location. Here we address knowledge limitations through research describing how eye movements change as a person learns to adopt an eccentric retinal locus. Using a gaze-contingent, eye tracking-guided paradigm to simulate central vision loss, 40 participants developed a PRL by engaging in an oculomotor and visual recognition task. After 12 training sessions, significant improvements were observed in six eye movement metrics addressing different aspects involved in learning to use a PRL: first saccade landing dispersion, saccadic re-referencing, saccadic precision, saccadic latency, percentage of useful trials, and fixation stability. Importantly, our analyses allowed separate examination of the stability of target fixation separately from the dispersion and precision of the landing location of saccades. These measures explained 50% of the across-subject variance in accuracy. Fixation stability and saccadic precision showed a strong, positive correlation. Although there was no statistically significant difference in rate of learning, individuals did tend to learn saccadic precision faster than fixation stability. Saccadic precision was also more associated with accuracy than fixation stability for the behavioral task. This suggests effective intervention strategies in low vision should address both fixation stability and saccadic precision.

Visual continuous recognition reveals behavioral and neural differences for short- and long-term scene memory.

Humans have a remarkably high capacity and long duration memory for complex scenes. Previous research documents the neural substrates that allow for efficient categorization of scenes from other complex stimuli like objects and faces, but the spatiotemporal neural dynamics underlying scene memory at timescales relevant to working and longer-term memory are less well understood. In the present study, we used high density EEG during a visual continuous recognition task in which new, old, and scrambled scenes consisting of color outdoor photographs were presented at an average rate 0.26 Hz. Old scenes were single repeated presentations occurring within either a short-term (< 20 s) or longer-term intervals of between 30 s and 3 min or 4 and 10 min. Overall recognition was far above chance, with better performance at shorter- than longer-term intervals. Sensor-level ANOVA and post hoc pairwise comparisons of event related potentials (ERPs) revealed three main findings: (1) occipital and parietal amplitudes distinguishing new and old from scrambled scenes; (2) frontal amplitudes distinguishing old from new scenes with a central positivity highest for hits compared to misses, false alarms and correct rejections; and (3) frontal and parietal changes from ∼300 to ∼600 ms distinguishing among old scenes previously encountered at short- and longer-term retention intervals. These findings reveal how distributed spatiotemporal neural changes evolve to support short- and longer-term recognition of complex scenes.

Attentive Feature Augmentation for Long-Tailed Visual Recognition

Deep neural networks have achieved great success on many visual recognition tasks. However, training data with a long-tailed distribution dramatically degenerates the performance of recognition models. In order to relieve this imbalance problem, an effective Long-Tailed Visual Recognition (LTVR) framework is proposed based on learned balance and robust features under long-tailed distribution circumstances. In this framework, a plug-and-play Attentive Feature Augmentation (AFA) module is designed to mine class-related and variation-related features of original samples via a novel hierarchical channel attention mechanism. Then, those features are aggregated to synthesize fake features to cope with the imbalance of the original dataset. Moreover, a Lay-Back Learning Schedule (LBLS) is developed to ensure a good initialization of feature embedding. Extensive experiments are conducted with a two-stage training method to verify the effectiveness of the proposed framework on both feature learning and classifier rebalancing in the long-tailed image recognition task. Experimental results show that, when trained with imbalanced datasets, the proposed framework achieves superior performance over the state-of-the-art methods.

Long-tailed visual recognition with deep models: A methodological survey and evaluation

In the real world, large-scale datasets for visual recognition typically exhibit a long-tailed distribution, where only a few classes contain adequate samples but the others have (much) fewer samples. With the advancement of data-hungry deep models for visual recognition, the low-tail power-law data distribution that biases the model training has attracted significant attention. When training with the long-tailed data, the majority classes dominate the training procedure, resulting in poor performance in instance-scarce classes. To tackle this problem, numerous strategies, such as re-sampling, cost-sensitive loss, meta-learning and transfer learning, have been proposed. This paper systematically reviews contemporary approaches for the long-tailed visual recognition task and categorizes these methods based on the stage applied as training, fine-tuning, and inference. Furthermore, we categorize training stage methods into data augmentation, re-sampling strategy, cost-sensitive loss, as well as multiple experts and transfer learning. Next, comprehensive comparisons are made in the balanced test set performance of long-tailed benchmarks and method robustness in diverse test distributions using metrics including top-1 accuracy, per-class accuracy, multi-class ROC AUC and Expected Calibration Error (ECE). At last, we outline the challenges in this field and future research trends. Our reviews and intriguing findings can be a tutorial for researchers working in the field of open-world deep learning.

Generative adversarial networks (GANs) for image augmentation in agriculture: A systematic review

In agricultural image analysis, optimal model performance is keenly pursued for better fulfilling visual recognition tasks (e.g., image classification, segmentation, object detection and localization), in the presence of challenges with biological variability and unstructured environments. Large-scale, balanced and ground-truthed image datasets are tremendously beneficial but most often difficult to obtain to fuel the development of highly performant models. As artificial intelligence through deep learning is impacting analysis and modeling of agricultural images, image augmentation plays a crucial role in boosting model performance while reducing manual efforts for image collection and labelling, by algorithmically creating and expanding datasets. Beyond traditional data augmentation techniques, generative adversarial network (GAN) invented in 2014 in the computer vision community, provides a suite of novel approaches that can learn good data representations and generate highly realistic samples. Since 2017, there has been a growth of research into GANs for image augmentation or synthesis in agriculture for improved model performance. This paper presents an overview of the evolution of GAN architectures followed by a first systematic review of various applications in agriculture and food systems (https://github.com/Derekabc/GANs-Agriculture), involving a diversity of visual recognition tasks for plant health conditions, weeds, fruits (preharvest), aquaculture, animal farming, plant phenotyping as well as postharvest detection of fruit defects. Challenges and opportunities of GANs are discussed for future research.

Visual Object Recognition From Single-Trial EEG Signals Using Machine Learning Wrapper Techniques.

Responses of the human brain to different visual stimuli elicit specific patterns in electroencephalography (EEG) signals. It is confirmed that by analyzing these patterns, we can recognize the category of the visited objects. However, high levels of noise and artifacts in EEG signals and the discrepancies between the recorded data from different subjects in visual object recognition task make classification of cognitive states of subjects a serious challenge. In this research, we present a framework for evaluating machine learning and wrapper channel selection algorithms used for classifying single-trial EEG signals recorded in response to photographic stimuli. It is shown that by correctly mapping the entire EEG data space to informative feature spaces (IFS), the performance of the classification methods can improve significantly. Results outperform the state-of-the-art results and confirm efficiency of the proposed feature selection methods in capturing the most informative EEG channels. This can help to achieve high separability of object categories in single-trial visual object recognition task.

Holistic processing of body stimuli: Evidence of body composite illusion in adults and children.

There is inconsistent evidence that human bodies are processed through holistic processing as it has been widely reported for faces. To assess how configural and holistic processes may develop with age, we administered a visual body recognition task assessing the presence of body inversion and composite illusion effects to white adults (114 participants, 77 women, aged between 18 and 35 years) and children (138 participants, 74 girls, aged between 6 and 11 years). Furthermore, to verify the presence of an own-age bias in body processing, we presented either child or adult bodies to both age groups. Adults and children showed reliable and comparable body inversion and composite illusion effects, confirming the use of configural and holistic body processing. Cross-sectional analysis showed that these perceptual strategies were already reliable in children aged 6-7 years and did not encounter significant changes across childhood. Although we found reliable body inversion and composite illusion effects for both own- and different-age bodies, results pointed to greater composite illusion effects for own-age bodies. This may suggest that sharing similar body structures might facilitate the holistic processing of others' bodies. These findings provide new insights into the development of body-specific perceptual processes and may have theoretical and clinical implications for the evaluation and treatment of body perception disorders in childhood. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Pneumonia Classification in Lung X-ray Images Using CNN Technique

Abstract— A fundamental phase in the technique of pneumonia diagnosis is the evaluation and categorization of lung disorders utilizing X-raypictures, especially during a crucial era such as the COVID19 pandemic, which is a kind of pneumonia. As a result of the growing number of cases, an automated approach with high classification accuracy is required to classify lung disorders. Due to its quickness and effectiveness when it comes to visual recognition tasks, CNN based segmentation has acquired a lot of traction in recent years. We present an implementation of CNN-based classifiertechniques utilize a domain adaptation approach to identify pneumonia and analyze the outcomes to choose the best model for the job depending on specific parameters in this paper. There are various models because this is a rapidly growing topic, and we will concentrate on the bestperforming methods relying on their structure, tier length and style, and categorization task assessment criteria. To begin, we look at the existing traditional approaches and supervised learning frameworks for segmentation. Then, depending on the reliability and damage functionality of the constructed models, we undertake a detailed evaluation and analysis. A rigorous examination of the findings is carried out in order to highlight the major concerns that need to be addressed. Keywords— Covid19, CNN, pneumonia, X-rays.

Memory-Based Jitter: Improving Visual Recognition on Long-Tailed Data with Diversity in Memory

This paper considers deep visual recognition on long-tailed data. To make our method general, we tackle two applied scenarios, i.e. , deep classification and deep metric learning. Under the long-tailed data distribution, the most classes (i.e., tail classes) only occupy relatively few samples and are prone to lack of within-class diversity. A radical solution is to augment the tail classes with higher diversity. To this end, we introduce a simple and reliable method named Memory-based Jitter (MBJ). We observe that during training, the deep model constantly changes its parameters after every iteration, yielding the phenomenon of weight jitters. Consequentially, given a same image as the input, two historical editions of the model generate two different features in the deeply-embedded space, resulting in feature jitters. Using a memory bank, we collect these (model or feature) jitters across multiple training iterations and get the so-called Memory-based Jitter. The accumulated jitters enhance the within-class diversity for the tail classes and consequentially improves long-tailed visual recognition. With slight modifications, MBJ is applicable for two fundamental visual recognition tasks, i.e., deep image classification and deep metric learning (on long-tailed data). Extensive experiments on five long-tailed classification benchmarks and two deep metric learning benchmarks demonstrate significant improvement. Moreover, the achieved performance are on par with the state of the art on both tasks.

Mutual Contrastive Learning for Visual Representation Learning

We present a collaborative learning method called Mutual Contrastive Learning (MCL) for general visual representation learning. The core idea of MCL is to perform mutual interaction and transfer of contrastive distributions among a cohort of networks. A crucial component of MCL is Interactive Contrastive Learning (ICL). Compared with vanilla contrastive learning, ICL can aggregate cross-network embedding information and maximize the lower bound to the mutual information between two networks. This enables each network to learn extra contrastive knowledge from others, leading to better feature representations for visual recognition tasks. We emphasize that the resulting MCL is conceptually simple yet empirically powerful. It is a generic framework that can be applied to both supervised and self-supervised representation learning. Experimental results on image classification and transfer learning to object detection show that MCL can lead to consistent performance gains, demonstrating that MCL can guide the network to generate better feature representations. Code is available at https://github.com/winycg/MCL.

Abstract 349: Segmentation Of Atherosclerotic Plaque Features From Histopathology Images Using Novel Deep Learning Techniques

Objective: Atherosclerotic plaques have a complex composition, consisting of inflammation, fibrosis, cholesterol crystals, hemorrhage, and/or calcification. The segmentation and quantification of plaque features in histopathology images form the foundation for studies evaluating plaque instability and the mechanisms that underlie the atherosclerotic process. Manual segmentation of plaque features from histology images is a tedious, time-consuming, and subjective visual recognition task. Herein, we present a fully automatic approach using state-of-the-art deep learning techniques to identify three major features of the atherosclerotic plaque: calcification, lipid core, and fibrosis. Methods: Plaques (n=70) were collected from patients who underwent a carotid endarterectomy at McGill University-affiliated hospitals. Hematoxylin and Eosin-stained sections were obtained from the region with the largest plaque burden. The “ground truth annotations” for lipid core, calcification, and fibrosis were performed manually by three blinded cardiovascular pathologists, using Sedeen Viewer. A total of 23,000 patches with 512x512 pixel size were extracted from our image dataset, and divided into train, validate, and test sets. Using Transfer Learning, multi-class U-Net models for semantic segmentation were trained on the patches to extract fibrosis, lipid, and calcification plaque features. Evaluation of model performance was based on the mean value of the Intersection over Union (Mean-IOU) between the prediction results and the “ground truth annotations”. Results: Our models resulted in an overall performance of 77% for test images, and a per-class performance for the three plaque features: fibrosis = 0.77±0.2, lipid core = 0.80±0.3, calcification = 0.75±0.25. However, a qualitative evaluation by the pathologists confirmed that the prediction results in fact outperformed the “ground truth annotations”, and detected non-annotated regions. Conclusion: To our knowledge, this is a first attempt at developing a fully automatic approach for atherosclerotic plaque feature segmentation from histology images. Our models can accelerate atherosclerosis research, by improving the speed, quality, and reproducibility of plaque analysis.

SFGNet detecting objects via spatial fine-grained feature and enhanced RPN with spatial context

Object detection, which is one of the most fundamental visual recognition tasks, has been a hotspot in computer vision. CNN (Convolutional Neural Networks) have been widely employed for building detector. Due to the success of RPN (Region Proposal Network), the two-stage detectors get both classification accuracy and precise regression bounding boxes. However, they still struggle in small-size object detection. In this paper, we present a deep network, namely Spatial Fine-Grained Network (SFGN). The SFGN that exploits Spatial Fine-Grained Features (SFGF) concatenates the higher resolution features, which is fine-grained with the low resolution features and high-level semantic by stacking spatial features for fine-grained features. An enhanced region proposal generator is proposed to get the objectless for small object to obtain a small set of proposal. The contextual information surrounding the region of interest is embedded using local spatial information for increasing the useful information and discriminating the background. For improving the detection performance, we use a simple yet surprisingly effective online hard example mining (OHEM) algorithm for training region proposal generator. It embeds an efficiently implemented soft non-maximum suppression (soft-NMS) for replacing with tradition NMS to obtain consistent improvements without increasing the computational complexity in inference. On PASCAL VOC 2007 and PASCAL VOC 2012 datasets, our SFGN improves baseline model from 81.2% mAP to 80.6% mAP. On MS COCO dataset, SFGN also performs better than baseline model. As intuition suggests, our detection results provide strong evidence that our SFGN improves detection accuracy, especially in small object test.

Time-Frequency Representations of Brain Oscillations: Which One Is Better?

Brain oscillations are thought to subserve important functions by organizing the dynamical landscape of neural circuits. The expression of such oscillations in neural signals is usually evaluated using time-frequency representations (TFR), which resolve oscillatory processes in both time and frequency. While a vast number of methods exist to compute TFRs, there is often no objective criterion to decide which one is better. In feature-rich data, such as that recorded from the brain, sources of noise and unrelated processes abound and contaminate results. The impact of these distractor sources is especially problematic, such that TFRs that are more robust to contaminants are expected to provide more useful representations. In addition, the minutiae of the techniques themselves impart better or worse time and frequency resolutions, which also influence the usefulness of the TFRs. Here, we introduce a methodology to evaluate the “quality” of TFRs of neural signals by quantifying how much information they retain about the experimental condition during visual stimulation and recognition tasks, in mice and humans, respectively. We used machine learning to discriminate between various experimental conditions based on TFRs computed with different methods. We found that various methods provide more or less informative TFRs depending on the characteristics of the data. In general, however, more advanced techniques, such as the superlet transform, seem to provide better results for complex time-frequency landscapes, such as those extracted from electroencephalography signals. Finally, we introduce a method based on feature perturbation that is able to quantify how much time-frequency components contribute to the correct discrimination among experimental conditions. The methodology introduced in the present study may be extended to other analyses of neural data, enabling the discovery of data features that are modulated by the experimental manipulation.

Grassmannian graph-attentional landmark selection for domain adaptation

Domain adaptation aims to leverage information from the source domain to improve the classification performance in the target domain. It mainly utilizes two schemes: sample reweighting and feature matching. While the first scheme allocates different weights to individual samples, the second scheme matches the feature of two domains using global structural statistics. The two schemes are complementary with each other, which are expected to jointly work for robust domain adaptation. Several methods combine the two schemes, but the underlying relationship of samples is insufficiently analyzed due to the neglect of the hierarchy of samples and the geometric properties between samples. To better combine the advantages of the two schemes, we propose a Grassmannian graph-attentional landmark selection (GGLS) framework for domain adaptation. GGLS presents a landmark selection scheme using attention-induced neighbors of the graphical structure of samples and performs distribution adaptation and knowledge adaptation over Grassmann manifold. the former treats the landmarks of each sample differently, and the latter avoids feature distortion and achieves better geometric properties. Experimental results on different real-world cross-domain visual recognition tasks demonstrate that GGLS provides better classification accuracies compared with state-of-the-art domain adaptation methods.

Spiking Neural Networks for Visual Place Recognition Via Weighted Neuronal Assignments

Spiking neural networks (SNNs) offer both compelling potential advantages, including energy efficiency and low latencies and challenges including the non-differentiable nature of event spikes. Much of the initial research in this area has converted deep neural networks to equivalent SNNs, but this conversion approach potentially negates some of the advantages of SNN-based approaches developed from scratch. One promising area for high-performance SNNs is template matching and image recognition. This research introduces the first high-performance SNN for the Visual Place Recognition (VPR) task: given a query image, the SNN has to find the closest match out of a list of reference images. At the core of this new system is a novel assignment scheme that implements a form of ambiguity-informed salience, by up-weighting single-place-encoding neurons and down-weighting "ambiguous" neurons that respond to multiple different reference places. In a range of experiments on the challenging Nordland, Oxford RobotCar, SPEDTest, Synthia, and St Lucia datasets, we show that our SNN achieves comparable VPR performance to state-of-the-art and classical techniques, and degrades gracefully in performance with an increasing number of reference places. Our results provide a significant milestone towards SNNs that can provide robust, energy-efficient, and low latency robot localization.

Enhanced task attention with adversarial learning for dynamic multi-task CNN

Multi-task deep learning is promising to solve multi-label multi-instance visual recognition tasks. However, flexible information sharing in the task group might bring performance bottlenecks to an individual task. To tackle this problem, we propose a novel learning framework of multi-task Convolutional Neural Network (CNN) to enhance task attention through conditionally tuning the Task Transfer Connections (TTC) with adversarial learning. For the dynamic multi-task CNN, we set up a shared subnet to extract shared features across multiple tasks and a task discriminator shared by all layers to distinguish features of all subnets. The adversarial training is introduced between the shared subnet and the task discriminator to guide each task subnet to focus on its specific task. To apply adversarial learning to the complex labeling system of multiple tasks, we design an even-label strategy for the multi-task model with a shared subnet to make adversarial learning feasible for the complex labeling system of multiple tasks. As a result, the proposed model can constrain the shared subnet’s learning unbiased to any single task and achieve task attention for all task subnets. Experimental results of the ablation study and the TTC analysis validate the effectiveness of the proposed approach.

Influences of First and Second Language Phonology on Spanish Children Learning to Read in English.

Children learning to read in two different orthographic systems are exposed to cross-linguistic interferences. We explored the effects of school (Monolingual, Bilingual) and grade (2nd, 4th, and 6th) on phonological activation during a visual word recognition task. Elementary school children from Spain completed a lexical decision task in English. The task included real words and pseudohomophones following Spanish or English phonological rules. Using the mouse-tracking paradigm, we analyzed errors, reaction times, and computer mouse movements. Children in the bilingual school performed better than children in the monolingual school. Children in higher grades performed better than children in lower grades. The interference effect of Spanish phonology was weak and became weaker in higher grades. Spanish children differentiate between first and second language grapheme-to-phoneme correspondences since early on in the educational process. In 6th grade, children from the bilingual school responded better to words and Spanish pseudohomophones, while children from the monolingual school were less distracted by the English pseudohomophones. Children in the bilingual school had stronger inhibition of Spanish (L1) phonology and stronger activation of English (L2) phonology. Instructional method plays an important role on the processing strategies Spanish children rely on when reading in English. School and grade influence the link between orthographic and phonological representations.

Object Detection Techniques based on Deep Learning: A Review

Object detection is a computer technique that searches digital images and videos for occurrences of meaningful subjects in particular categories (such as people, buildings, and automobiles). It is related to computer vision and image processing. Two well-studied aspects of identification are facial and pedestrian detection. Object detection is useful in a wide range of visual recognition tasks, including image retrieval and video monitoring. The object detection algorithm has been improved many times to improve the performance in terms of speed and accuracy. “Due to the tireless efforts of many researchers, deep learning algorithms are rapidly improving their object detection performance. Pedestrian detection, medical imaging, robotics, self-driving cars, face recognition and other popular applications have reduced labor in many areas.” It is used in a wide variety of industries, with applications range from individual safeguarding to business productivity. It is a fundamental component of driver assist systems and driverless cars, which allows automobiles to identify driving lanes and pedestrians to avoid any accidents.

Image classification with parallel KPCA‐PCA network

AbstractPrincipal component analysis (PCA) is widely used in computer vision for object detection. In this article, we take advantage of the algorithms of PCA and kernel principal component analysis (KPCA) to construct a deep learning model named parallel KPCA‐PCA network (PK‐PCANet). In the proposed model, both of the given PCA and KPCA algorithm are aiming to calculate the filters that will be used in the following convolution layers. The extracted features from PCANet and KPCANet are fused by the strategy of parallel feature fusion. With the aim of reducing the dimensionality of the learned features, the algorithm of compressed sensing is incorporated in the proposed network. According to the cooperative advantages of deep learning network and compressed sensing, the proposed PK‐PCANet model obtains some improvements in several visual recognition tasks. Extensively experiments are performed on face recognition, hand‐written digit recognition and object classification, and the experimental results on various image classification benchmarks such as Extended Yale B, AR, MNIST, CIFAR‐10, and VOC 2007 validated the efficiency of the proposed method of PK‐PCANet.

Artificial Intelligence-Based Assistance System for Visual Inspection of X-ray Scatter Grids.

Convolutional neural network (CNN)-based approaches have recently led to major performance steps in visual recognition tasks. However, only a few industrial applications are described in the literature. In this paper, an object detection application for visual quality evaluation of X-ray scatter grids is described and evaluated. To detect the small defects on the 4K input images, a sliding window approach is chosen. A special characteristic of the selected approach is the aggregation of overlapping prediction results by applying a 2D scalar field. The final system is able to detect 90% of the relevant defects, taking a precision score of 25% into account. A practical examination of the effectiveness elaborates the potential of the approach, improving the detection results of the inspection process by over 13%.