Neural Network For Object Recognition Research Articles

Direct training high-performance spiking neural networks for object recognition and detection.

The spiking neural network (SNN) is a bionic model that is energy-efficient when implemented on neuromorphic hardwares. The non-differentiability of the spiking signals and the complicated neural dynamics make direct training of high-performance SNNs a great challenge. There are numerous crucial issues to explore for the deployment of direct training SNNs, such as gradient vanishing and explosion, spiking signal decoding, and applications in upstream tasks. To address gradient vanishing, we introduce a binary selection gate into the basic residual block and propose spiking gate (SG) ResNet to implement residual learning in SNNs. We propose two appropriate representations of the gate signal and verify that SG ResNet can overcome gradient vanishing or explosion by analyzing the gradient backpropagation. For the spiking signal decoding, a better decoding scheme than rate coding is achieved by our attention spike decoder (ASD), which dynamically assigns weights to spiking signals along the temporal, channel, and spatial dimensions. The SG ResNet and ASD modules are evaluated on multiple object recognition datasets, including the static ImageNet, CIFAR-100, CIFAR-10, and neuromorphic DVS-CIFAR10 datasets. Superior accuracy is demonstrated with a tiny simulation time step of four, specifically 94.52% top-1 accuracy on CIFAR-10 and 75.64% top-1 accuracy on CIFAR-100. Spiking RetinaNet is proposed using SG ResNet as the backbone and ASD module for information decoding as the first direct-training hybrid SNN-ANN detector for RGB images. Spiking RetinaNet with a SG ResNet34 backbone achieves an mAP of 0.296 on the object detection dataset MSCOCO.

Models of vision need some action.

Bowers et al. focus their criticisms on research that compares behavioral and brain data from the ventral stream with a class of deep neural networks for object recognition. While they are right to identify issues with current benchmarking research programs, they overlook a much more fundamental limitation of this literature: Disregarding the importance of action and interaction for perception.

АЛГОРИТМ ФОРМУВАННЯ НАБОРУ АПРІОРНИХ ДАНИХ НЕЙРОННОЇ МЕРЕЖІ ДЛЯ ОБРОБКИ ЦИФРОВИХ АЕРОЗНІМКІВ

Analysis of the use of unmanned aerial systems in the combat zone indicates a constant increase in the requirements for intelligence data. One of the ways to increase the effectiveness of UaV application is the use of artificial intelligence methods. The basis for building a reliable neural network model is a large amount of various data, which helps to more accurately summarize information about the given task. The article considers an approach for increasing the accuracy of object image classification by convolutional neural networks based on data augmentation, which differs from existing ones in its adaptation to shooting factors and the specificity of aerial reconnaissance objects. An important and most time-consuming step in building an accurate machine learning model is finding and annotating the data that will be used to train and test the accuracy of the neural network. The accuracy and stability of the network in real conditions depends on the amount of collected data. To date, such methods of object image augmentation as geometric transformations, color correction, and spatial image filtering have been well described and analyzed. The possibilities of optimal combinations of data augmentation methods to achieve the desired generalization of poorly visible invariant features of objects remain unexplored at the moment. Taking into account the conducted research, an approach was proposed for the formation of a set of a priori data of a neural network for object recognition on digital aerial photographs, which will significantly reduce the complexity of the process of collecting the necessary data and replace it with magnification methods that are much simpler, consume less computing resources, and increase the accuracy of work convolutional neural networks, simulation of the use of the proposed approach was carried out. Keywords: unmanned aerial vehicle; convolutional neural network; data augmentation; automated processing of digital aerial photographs.

AutoML-Based Neural Architecture Search for Object Recognition in Satellite Imagery

Advancements in optical satellite hardware and lowered costs for satellite launches raised the high demand for geospatial intelligence. The object recognition problem in multi-spectral satellite imagery carries dataset properties unique to this problem. Perspective distortion, resolution variability, data spectrality, and other features make it difficult for a specific human-invented neural network to perform well on a dispersed type of scenery, ranging data quality, and different objects. UNET, MACU, and other manually designed network architectures deliver high-performance results for accuracy and prediction speed in large objects. However, once trained on different datasets, the performance drops and requires manual recalibration or further configuration testing to adjust the neural network architecture. To solve these issues, AutoML-based techniques can be employed. In this paper, we focus on Neural Architecture Search that is capable of obtaining a well-performing network configuration without human manual intervention. Firstly, we conducted detailed testing on the top four performing neural networks for object recognition in satellite imagery to compare their performance: FastFCN, DeepLabv3, UNET, and MACU. Then we applied and further developed a Neural Architecture Search technique for the best-performing manually designed MACU by optimizing a search space at the artificial neuron cellular level of the network. Several NAS-MACU versions were explored and evaluated. Our developed AutoML process generated a NAS-MACU neural network that produced better performance compared with MACU, especially in a low-information intensity environment. The experimental investigation was performed on our annotated and updated publicly available satellite imagery dataset. We can state that the application of the Neural Architecture Search procedure has the capability to be applied across various datasets and object recognition problems within the remote sensing research field.

The Simulation of Autonomous Vehicle Using ROS2 Based on Convolutional Neural Networks for Object Recognition

The main justification for implementing an Autonomous Vehicle (AV) system in the real world is the safety aspect of driving, because if there is an error in driving then the error will become a gap that can threaten the safety of the driver himself and other drivers, therefore an AV system is made to reduce driver errors. in driving. The aim of this research is to implement one of the parts of the AV system, that is object recognition, and in this study, we also conduct an experiment with simulating the object recognition feature that has been implemented in order to get more concrete results. Architectural object recognition is designed to extract key features from traffic sign images, the traffic sign detection uses the customized Convolutional Neural Networks (CNNs) architecture. After the architectural has been implemented, training will be carried out using Custom Traffic Sign Dataset and experiments will also be conducted to simulate object recognition by applying ROS2 as a car robotic system that represents a car's functionality system in the real world. the results of this study for the implementation of the modified CNNs architecture is 99.96% and the results of the simulations carried out show that the prototype can detect traffic signs objects with a distance of 10m

Warping of Radar Data Into Camera Image for Cross-Modal Supervision in Automotive Applications

We present an approach to automatically generate semantic labels for real recordings of automotive range-Doppler (RD) radar spectra. Such labels are required when training a neural network for object recognition from radar data. The automatic labeling approach rests on the simultaneous recording of camera and lidar data in addition to the radar spectrum. By warping radar spectra into the camera image, state-of-the-art object recognition algorithms can be applied to label relevant objects, such as cars, in the camera image. The warping operation is designed to be fully differentiable, which allows backpropagating the gradient computed on the camera image through the warping operation to the neural network operating on the radar data. As the warping operation relies on accurate scene flow estimation, we further propose a novel scene flow estimation algorithm which exploits information from camera, lidar and radar sensors. The proposed scene flow estimation approach is compared against a state-of-the-art scene flow algorithm, and it outperforms it by approximately 30% w.r.t. mean average error. The feasibility of the overall framework for automatic label generation for RD spectra is verified by evaluating the performance of neural networks trained with the proposed framework for Direction-of-Arrival estimation.

Recurrent processing improves occluded object recognition and gives rise to perceptual hysteresis.

Over the past decades, object recognition has been predominantly studied and modelled as a feedforward process. This notion was supported by the fast response times in psychophysical and neurophysiological experiments and the recent success of deep feedforward neural networks for object recognition. Recently, however, this prevalent view has shifted and recurrent connectivity in the brain is now believed to contribute significantly to object recognition — especially under challenging conditions, including the recognition of partially occluded objects. Moreover, recurrent dynamics might be the key to understanding perceptual phenomena such as perceptual hysteresis. In this work we investigate if and how artificial neural networks can benefit from recurrent connections. We systematically compare architectures comprised of bottom-up, lateral, and top-down connections. To evaluate the impact of recurrent connections for occluded object recognition, we introduce three stereoscopic occluded object datasets, which span the range from classifying partially occluded hand-written digits to recognizing three-dimensional objects. We find that recurrent architectures perform significantly better than parameter-matched feedforward models. An analysis of the hidden representation of the models suggests that occluders are progressively discounted in later time steps of processing. We demonstrate that feedback can correct the initial misclassifications over time and that the recurrent dynamics lead to perceptual hysteresis. Overall, our results emphasize the importance of recurrent feedback for object recognition in difficult situations.

Small object recognition with trainable lens

Lenses are used to form images of objects. They follow a parabolic profile, as dictated by the physics of imaging optics. The clarity of images is essential for object recognition. However, challenging image conditions limit the capability of forming clear images. This happens when objects are very small or far away. Such images make it difficult to apply neural networks for object recognition. Here, we overcome this challenge by replacing the parabolic lens with a trainable lens, which lets us extend the learning process from the digital into the physical world. The lens profile is parameterized by over 10 000 trainable parameters. When used for recognizing small objects with low resolution, the profile adapts to maximize the accuracy of the recognition. The resulting profile could be significantly different from a typical parabolic lens. We show that the object recognition accuracy is improved by more than 25% when the objects are 16 times smaller than their original size. Besides, incorporating the trainable lens before digital computing adds minimal computational time. Our method has potential application in biology, such as cell detection, in the semiconductor industry, such as detecting defects, and in salvage.

Inception recurrent convolutional neural network for object recognition

Deep convolutional neural network (DCNN) is an influential tool for solving various problems in machine learning and computer vision. Recurrent connectivity is a very important component of visual information processing within the human brain. The idea of recurrent connectivity is rarely applied within convolutional layers, the exceptions being a couple of DCNN architectures including recurrent convolutional neural network (RCNN) in Liang and Hu (in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2015) and Pinheiro and Collobert (in: ICML, 2014). On the other hand, the Inception network architecture has become popular among the computer vision community (Szegedy et al. in Inception-v4, Inception-ResNet and the impact of Residual connections on learning, 2016. arXiv:1602.07261 ). In this paper, we introduce a deep learning architecture called the Inception Recurrent Convolutional Neural Network (IRCNN), which utilizes the power of an Inception network combined with recurrent convolutional layers. Although the inputs are static, the recurrent property plays a huge role in modeling the contextual information for object recognition tasks and thus improves overall training and testing accuracy. In addition, this proposed architecture generalizes both Inception and RCNN models. We have empirically evaluated the recognition performance of the proposed IRCNN model using different benchmark datasets such as MNIST, CIFAR-10, CIFAR-100, and SVHN. The experimental results show higher recognition accuracy when compared to most of the popular DCNNs including the RCNN. Furthermore, we have investigated IRCNN performance against equivalent Inception networks (EIN) and equivalent Inception–Residual networks (EIRN) using the CIFAR-100 dataset. When using the augmented CIFAR-100 dataset, we achieved about 3.5%, 3.47% and 2.54% improvement in classification accuracy compared to the RCNN, EIN, and EIRN respectively. We have also conducted experiment on Tiny ImageNet-200 dataset with IRCNN, EIN, EIRN, RCNN, DenseNet in Huang et al. (Densely connected convolutional networks, 2016. arXiv:1608.06993 ), and DenseNet with Recurrent Convolution Layer, where the proposed model shows significantly better performance against baseline models.

Overview of three-dimensional integral imaging-based object recognition in low illumination conditions with visible range image sensors

We overview three-dimensional (3D) integral imaging-based object recognition in low illumination conditions. Imaging in very low illumination conditions, especially using passive, visible-range image sensors, remains a challenging endeavor that is particularly complicated by read-noise dominant images and provides unsatisfactory results when using conventional two-dimensional imaging strategies in photon-starved conditions. However, using passive three-dimensional integral imaging, which is optimal in a maximum likelihood sense, we are able to significantly improve imaging capabilities under low illumination conditions and allow for object detection and recognition. We overview reported work on 3D integral imaging object visualization, and recognition in low light including recent work utilizing convolutional neural networks for object recognition in very low illumination conditions.

Deep Learning Based Object Recognition Using Physically-Realistic Synthetic Depth Scenes

Recognizing objects and estimating their poses have a wide range of application in robotics. For instance, to grasp objects, robots need the position and orientation of objects in 3D. The task becomes challenging in a cluttered environment with different types of objects. A popular approach to tackle this problem is to utilize a deep neural network for object recognition. However, deep learning-based object detection in cluttered environments requires a substantial amount of data. Collection of these data requires time and extensive human labor for manual labeling. In this study, our objective was the development and validation of a deep object recognition framework using a synthetic depth image dataset. We synthetically generated a depth image dataset of 22 objects randomly placed in a 0.5 m × 0.5 m × 0.1 m box, and automatically labeled all objects with an occlusion rate below 70%. Faster Region Convolutional Neural Network (R-CNN) architecture was adopted for training using a dataset of 800,000 synthetic depth images, and its performance was tested on a real-world depth image dataset consisting of 2000 samples. Deep object recognizer has 40.96% detection accuracy on the real depth images and 93.5% on the synthetic depth images. Training the deep learning model with noise-added synthetic images improves the recognition accuracy for real images to 46.3%. The object detection framework can be trained on synthetically generated depth data, and then employed for object recognition on the real depth data in a cluttered environment. Synthetic depth data-based deep object detection has the potential to substantially decrease the time and human effort required for the extensive data collection and labeling.

People Infer Recursive Visual Concepts from Just a Few Examples

Machine learning has made major advances in categorizing objects in images, yet the best algorithms miss important aspects of how people learn and think about categories. People can learn richer concepts from fewer examples, including causal models that explain how members of a category are formed. Here, we explore the limits of this human ability to infer causal “programs”—latent generating processes with nontrivial algorithmic properties—from one, two, or three visual examples. People were asked to extrapolate the programs in several ways, for both classifying and generating new examples. As a theory of these inductive abilities, we present a Bayesian program learning model that searches the space of programs for the best explanation of the observations. Although variable, people’s judgments are broadly consistent with the model and inconsistent with several alternatives, including a pretrained deep neural network for object recognition, indicating that people can learn and reason with rich algorithmic abstractions from sparse input data.

3D convolutional neural network for object recognition: a review

Recognition of an object from an image or image sequences is an important task in computer vision. It is an important low-level image processing operation and plays a crucial role in many real-world applications. The challenges involved in object recognition are multi-model, multi-pose, complicated background, and depth variations. Recently developed methods have dealt with these challenges and have reported remarkable results for 3D objects. In this paper, a comprehensive overview of recent advances in 3D object recognition using Convolutional Neural Networks (CNN) has been presented. Along with the latest progress in 3D images, general overview of object recognition of 2D, 2.5D, and 3D images is presented.

Boosted Convolutional Neural Network for object recognition at large scale

During the last few years, object recognition has received a big of interest in an attempt to make use of the large scale image datasets. Object recognition allows understanding image based on the objects that it contains. The success of the deep learning based methods in recognizing objects has encouraged recent works to follow this approach. In this paper, we propose a Boosted Convolutional Neural Network approach for object recognition. Our approach uses a very deep convolutional neural network reinforced by adding Boosted Blocks. These Boosted Blocks consist of a succession of convolutional layers boosted by using a Multi-Bias Nonlinear Activation function, that enriches the expressive power of the network, as well as a Concatenated Rectified Linear Unit function which ensures the preservation of all the information after the convolutional layer. Besides, inspired by the visual system of the human brain, our Boosted Convolutional Layer is designed following a recurrent structure. In addition, rather than using the classical max-pooling, our Boosted Convolutional Neural Network is improved by applying Generalizing pooling which allows pooling to adapt to complex and variable patterns. Furthermore, the Spatial Pyramid Pooling after the last Boosted Block has been conducted after the Boosted Block in order to remove the fixed-size constraint of input image. Our approach is evaluated on four different object recognition benchmarks: Pascal VOC 2007, Pascal VOC 2012, CIFAR-10 and the larger dataset ILSVRC-2012. These datasets are widely used by the recent object recognition methods. The experimental results validate the efficiency of our method in comparison with other methods from the literature.

Active Object Detection Model with Deep Neural Network for Object Recognition

International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.

Improved inception-residual convolutional neural network for object recognition

Machine learning and computer vision have driven many of the greatest advances in the modeling of Deep Convolutional Neural Networks (DCNNs). Nowadays, most of the research has been focused on improving recognition accuracy with better DCNN models and learning approaches. The recurrent convolutional approach is not applied very much, other than in a few DCNN architectures. On the other hand, Inception-v4 and Residual networks have promptly become popular among computer the vision community. In this paper, we introduce a new DCNN model called the Inception Recurrent Residual Convolutional Neural Network (IRRCNN), which utilizes the power of the Recurrent Convolutional Neural Network (RCNN), the Inception network, and the Residual network. This approach improves the recognition accuracy of the Inception-residual network with same number of network parameters. In addition, this proposed architecture generalizes the Inception network, the RCNN, and the Residual network with significantly improved training accuracy. We have empirically evaluated the performance of the IRRCNN model on different benchmarks including CIFAR-10, CIFAR-100, TinyImageNet-200, and CU3D-100. The experimental results show higher recognition accuracy against most of the popular DCNN models including the RCNN. We have also investigated the performance of the IRRCNN approach against the Equivalent Inception Network (EIN) and the Equivalent Inception Residual Network (EIRN) counterpart on the CIFAR-100 dataset. We report around 4.53, 4.49 and 3.56% improvement in classification accuracy compared with the RCNN, EIN, and EIRN on the CIFAR-100 dataset respectively. Furthermore, the experiment has been conducted on the TinyImageNet-200 and CU3D-100 datasets where the IRRCNN provides better testing accuracy compared to the Inception Recurrent CNN, the EIN, the EIRN, Inception-v3, and Wide Residual Networks.

Adversarial Zero-shot Learning With Semantic Augmentation

In situations in which labels are expensive or difficult to obtain, deep neural networks for object recognition often suffer to achieve fair performance. Zero-shot learning is dedicated to this problem. It aims to recognize objects of unseen classes by transferring knowledge from seen classes via a shared intermediate representation. Using the manifold structure of seen training samples is widely regarded as important to learn a robust mapping between samples and the intermediate representation, which is crucial for transferring the knowledge. However, their irregular structures, such as the lack in variation of samples for certain classes and highly overlapping clusters of different classes, may result in an inappropriate mapping. Additionally, in a high dimensional mapping space, the hubness problem may arise, in which one of the unseen classes has a high possibility to be assigned to samples of different classes. To mitigate such problems, we use a generative adversarial network to synthesize samples with specified semantics to cover a higher diversity of given classes and interpolated semantics of pairs of classes. We propose a simple yet effective method for applying the augmented semantics to the hinge loss functions to learn a robust mapping. The proposed method was extensively evaluated on small- and large-scale datasets, showing a significant improvement over state-of-the-art methods.

STDP-based spiking deep convolutional neural networks for object recognition

Previous studies have shown that spike-timing-dependent plasticity (STDP) can be used in spiking neural networks (SNN) to extract visual features of low or intermediate complexity in an unsupervised manner. These studies, however, used relatively shallow architectures, and only one layer was trainable. Another line of research has demonstrated – using rate-based neural networks trained with back-propagation – that having many layers increases the recognition robustness, an approach known as deep learning. We thus designed a deep SNN, comprising several convolutional (trainable with STDP) and pooling layers. We used a temporal coding scheme where the most strongly activated neurons fire first, and less activated neurons fire later or not at all. The network was exposed to natural images. Thanks to STDP, neurons progressively learned features corresponding to prototypical patterns that were both salient and frequent. Only a few tens of examples per category were required and no label was needed. After learning, the complexity of the extracted features increased along the hierarchy, from edge detectors in the first layer to object prototypes in the last layer. Coding was very sparse, with only a few thousands spikes per image, and in some cases the object category could be reasonably well inferred from the activity of a single higher-order neuron. More generally, the activity of a few hundreds of such neurons contained robust category information, as demonstrated using a classifier on Caltech 101, ETH-80, and MNIST databases. We also demonstrate the superiority of STDP over other unsupervised techniques such as random crops (HMAX) or auto-encoders. Taken together, our results suggest that the combination of STDP with latency coding may be a key to understanding the way that the primate visual system learns, its remarkable processing speed and its low energy consumption. These mechanisms are also interesting for artificial vision systems, particularly for hardware solutions.

Coupled-learning convolutional neural networks for object recognition

Recently, convolutional neural networks (CNN) have been attracting considerable attention in various computer vision tasks. Motivated by neuroscience, CNN has several similar properties with the learning process of human brain. A prominent difference is that each CNN is an independent learning process while the effective interaction/communication between people can play important role in the human visual system. Inspired by this fact, we proposed a novel Coupled-learning Convolutional Neural Network (Co-CNN) for the task of object recognition, which boosts its discriminative capability by employing the dynamic interaction between neural networks. Contrary to existing network architectures posing the network optimization problem as an isolated learning process, the intuition behind the Co-CNN framework is that the coupled learning mechanism may prevent the algorithm away from over-fitting to one or more particular objective functions. The proposed Co-CNN framework has three unique characteristics: (1) Co-CNN, which is a novel deep network learning framework, can simultaneously optimize both neural networks with same/different structures. (2) The learned semantic information, which can be gradually mined from neural networks, is employed to guide the communication between neural networks. (3) Co-CNN well incorporates the coupled-learning mechanism into the process of learning neural networks, and then further improve the recognition performance of neural networks by adopting the learned semantic information. Comprehensive evaluations on five benchmark datasets (CIFAR-10, CIFAR-100, MNIST, SVHN and Imagenet) well demonstrate the significant superiority of our proposed Co-CNN framework over other existing algorithms.

BLSTM Recurrent Neural Network for Object Recognition

Multi-object relationship information can help eliminate some incorrect combinations or locations of objects. Moreover, it is favorable to extract scene information for object recognition. In this paper, we introduce a new way to generate image representation and propose a deep learning framework to fuse the contextual dependencies among objects and scene information in an image. It adopts a bidirectional long short-term memory recurrent neural network (BLSTM-RNN) to deal with the problem of variable-length sequence produced by local detectors in different images. Then it is applied to the existing tree context model for further recognition. Experimental results on SUN09 dataset show that our model outperforms the state-of the-art object localization methods.