Approach For Visual Recognition Research Articles

A Deep Learning Approach Visual Recognition of Bird Species in Noisy Environments

In this paper, we propose a deep learning approach for visual recognition of bird species in noisy environments. Bird species recognition has been a challenging task due to the high variation in bird appearances and the presence of noise and clutter in natural environments. Our approach utilizes a deep convolutional neural network (CNN) to learn discriminative features from bird images and classify them into different species. We also incorporate data augmentation techniques to increase the diversity of the training data and improve the robustness of the model. To address the issue of noisy environments, we introduce a novel noise-robust loss function that penalizes the model for incorrect predictions caused by noise. We evaluate our approach on a dataset of bird images collected from diverse environments and compare it with state-of-the-art methods. Our results demonstrate that our approach achieves superior performance in both clean and noisy environments, highlighting the effectiveness of our noise-robust loss function. Our approach has the potential to be applied in real-world scenarios for bird species recognition and conservation.

A Smart Solution for Sustainable Cotton Farming: A Machine Learning Approach for Visual Recognition of Leaf Diseases

Cotton leaf diseases pose significant threats to sustainable farming practices, leading to yield losses and economic burdens for cotton growers worldwide. In this paper, we propose a smart solution for efficient and accurate detection of cotton leaf diseases using machine learning techniques. Our approach leverages a convolutional neural network (CNN) architecture specifically designed for visual recognition of leaf diseases. To train and optimize the CNN model, we employ a genetic algorithm that enhances the learning process and improves classification performance. The proposed model is trained and evaluated on a comprehensive dataset containing six classes of cotton leaf diseases, namely Aphids, Army worm, Bacterial Blight, Powdery Mildew, Target spot, and healthy leaves. Experimental results demonstrate the effectiveness of our proposed method, achieving an overall accuracy of 97% on the test set. Comparative analyses with existing studies and methodologies reveal the superior performance of our approach, showcasing its potential for practical implementation in the field of cotton leaf disease detection. The outcomes of this study have significant implications for farmers, agronomists, and agricultural organizations, enabling them to make informed decisions and take timely actions to protect their crops and enhance productivity.

Scalability of knowledge distillation in incremental deep learning for fast object detection

Visual recognition requires incremental learning to scale its underlying deep learning models with continuous data growth. The existing scalability challenge is maintaining the balance between effectiveness (accuracy) and efficiency (computational requirements) due to the rapidly increasing storage demand, computational time, and memory usage for processing both the old and new data. This paper aims to investigate the scalability of the incremental deep learning approach for visual recognition, specifically for fast object detection applications. The experimental study demonstrates knowledge retention and computational expense of training-at-once, compared to incremental learning with knowledge transfer and distillation. The experiment was based on a state-of-the-art object detector, which was extended to incorporate knowledge transfer and distillation to benchmark three training approaches, namely, training-at-once, transfer learning without, and with distillation. The experimental results and analysis examined the pros and cons of each training approach while adjusting some key parameters, focusing on comparing the accuracy of new classes, knowledge retention of old classes, data storage, computation time, and memory usage. Training-at-once (the baseline) yielded the highest accuracy of both new and old classes, at the expense of the largest storage and memory usage. Compared to the baseline, both transfer learning approaches saved the storage requirement by −73% but with an increased computation time of ＋53%. Transfer learning with distillation was important for knowledge retention, maintaining 96% accuracy with old classes, which indicates its ability to handle long-term incremental learning. Compared to using distillation, transfer learning without distillation was able to achieve slightly better accuracy with new classes (−53% compared to −60%), less memory usage (−65% compared to ＋26%), but at the expense of forgetting old classes (−100%). This study confirmed that distillation loss could help balance the accuracy of old and new object classes while maintaining all the benefits of incremental learning. The experiments using varied key parameters across all training approaches confirmed that training batch size and number of assigned classes play an important role in maintaining the accuracy of new classes, retaining the knowledge of old classes, and reducing the computational cost.

Cooperative density-aware representation learning for few-shot visual recognition

Few-shot visual recognition has achieved remarkable advances along with the rise of deep learning. Its goal is to learn the model parameter from the base category for transferring it to the novel category with limited annotations. However, most of the existing few-shot visual recognition approaches mainly focus on extracting a global feature representation of the sample, which fails to encode the semantic information. To alleviate this issue, this paper presents a novel cooperative density-aware representation learning approach for few-shot visual recognition. Specifically, we first yield the high-level semantic features of the query set and the support set by leveraging a shared convolutional neural network. A cooperative density loss module is then designed to optimize the model to form the discriminative features by incorporating the density global classification loss and the density few-shot loss. The density few-shot loss conducts the semantic alignment with regional features by the mutual information finding manner while the density global classification loss supervises each regional feature lead to more precise classification. Comprehensive experiments in few-shot visual recognition benchmarks validate the effectiveness and superiority of our proposed approach, and elaborate ablations explain the utility of different modules.

Visual-Depth Matching Network: Deep RGB-D Domain Adaptation With Unequal Categories.

Existing domain adaptation (DA) methods generally assume that different domains have identical label space, and the training data are only sampled from a single domain. This unrealistic assumption is quite restricted for real-world applications, since it neglects the more practical scenario, where the source domain can contain the categories that are not shared by the target domain, and the training data can be collected from multiple modalities. In this article, we address a more difficult but practical problem, which recognizes RGB images through training on RGB-D data under the label space inequality scenario. There are three challenges in this task: 1) source and target domains are affected by the domain mismatch issue, which results in that the trained models perform imperfectly on the test data; 2) depth images are absent in the target domain (e.g., target images are captured by smartphones), when the source domain contains both the RGB and depth data. It makes the ordinary visual recognition approaches hardly applied to this task; and 3) in the real world, the source and target domains always have different numbers of categories, which would result in a negative transfer bottleneck being more prominent. Toward tackling the above challenges, we formulate a deep model, called visual-depth matching network (VDMN), where two new modules and a matching component can be trained in an end-to-end fashion jointly to identify the common and outlier categories effectively. The significance of VDMN is that it can take advantage of depth information and handle the domain distribution mismatch under label inequality simultaneously. The experimental results reveal that VDMN exceeds the state-of-the-art performance on various DA datasets, especially under the label inequality scenario.

Fine-Grained Visual Recognition in Mobile Augmented Reality for Technical Support.

Augmented Reality is increasingly explored as the new medium for two-way remote collaboration applications to guide the participants more effectively and efficiently via visual instructions. As users strive for more natural interaction and automation in augmented reality applications, new visual recognition techniques are needed to enhance the user experience. Although simple object recognition is often used in augmented reality towards this goal, most collaboration tasks are too complex for such recognition algorithms to suffice. In this paper, we propose a fine-grained visual recognition approach for mobile augmented reality, which leverages RGB video frames and sparse depth feature points identified in real-time, as well as camera pose data to detect various visual states of an object. We demonstrate the value of our approach through a mobile application designed for hardware support, which automatically detects the state of an object to present the right set of information in the right context.

A convolutional neural network approach for visual recognition in wheel production lines

China has been the world’s largest automotive manufacturing country since 2008. The automotive wheel industry in China has been growing steadily in pace with the automobile industry. Visual recognition system that automatically classifies wheel types is a key component in the wheel production line. Traditional recognition methods are mainly based on extracted feature matching. Their accuracy, robustness, and processing speed are often compromised considerably in actual production. To overcome this problem, we proposed a convolutional neural network approach to adaptively classify wheel types in actual production lines with a complex visual background. The essential steps to achieve wheel identification include image acquisition, image preprocessing, and classification. The image differencing algorithm and histogram technique are developed on acquired wheel images to remove track disturbances. The wheel images after image processing were organized into training and test sets. This approach improved the residual network model ResNet-18 and then evaluated this model based on the wheel test data. Experiments showed that this method can obtain an accuracy over 98% on nearly 70,000 wheel images and its single image processing time can reach millisecond level.

Beyond Visual Retargeting: A Feature Retargeting Approach for Visual Recognition and Its Applications

The popularity of mobile applications has greatly enriched and facilitated our lives. However, the rapid increase of digital images and the problem of narrow bandwidth of the wireless network call for an appropriate approach to reduce the amount of data transmitted over the wireless network (i.e., low bit-rate transmission) while ensuring high recognition accuracy at the cloud. We propose a simple and effective feature retargeting (FR) approach for retargeting an image while preserving the representative local features (e.g., SIFT, SURF, and BRIEF) in the image. Our feature retargeting approach aims at low bit-rate visual recognition instead of high-quality visual perception that visual retargeting methods dedicate to. Our algorithm consists of two key novelties: estimating feature saliency and retargeting image: Estimating feature saliency focuses on predicting the relative importance of different features in an image by analyzing uniqueness in a specific context; Retargeting image aims at finding the optimal resolution for the retargeted image to maximize feature-saliency energy. We evaluate the proposed approach for two different applications in three large data sets and observe that our FR approach consistently outperforms state-of-the-art retargeting algorithms, resulting in both higher precision and lower bit-rates. We also demonstrate that even when the resolution of source image is reduced greatly, e.g., 1/7 original size, our algorithm produces superior results as compared with other approaches.

Deep Localized Metric Learning

Metric learning has been widely used in many visual analysis applications, which learns new distance metrics to measure the similarities of samples effectively. Conventional metric learning methods learn a single linear Mahalanobis metric, yet such linear projections are not powerful enough to capture the nonlinear relationships. Recently, deep metric learning approaches, such as discriminative deep metric learning and deep transfer metric learning, have been introduced to fully exploit the nonlinearity of samples by learning hierarchical nonlinear transformations. However, these methods only learn holistic metrics over the input space and are limited for the heterogeneous data sets, where data varies locally. In this paper, we propose a deep localized metric learning approach for visual recognition by learning multiple fine-grained deep localized metrics. We first learn $K$ local subspaces and one holistic subspace with the K-auto-encoders-based clustering. Then, given an input pair, we compute its localized distance on each learned subspace and obtain the final distance representation. Finally, we train the entire neural networks to ensure the distances of positive pairs smaller than negative pairs by a large margin. Experimental results on three visual recognition applications, including face recognition, person re-identification, and scene recognition, show that our DLML outperforms most existing metric learning approaches.

Sharable and Individual Multi-View Metric Learning.

This paper presents a sharable and individual multi-view metric learning (MvML) approach for visual recognition. Unlike conventional metric leaning methods which learn a distance metric on either a single type of feature representation or a concatenated representation of multiple types of features, the proposed MvML jointly learns an optimal combination of multiple distance metrics on multi-view representations, where not only it learns an individual distance metric for each view to retain its specific property but also a shared representation for different views in a unified latent subspace to preserve the common properties. The objective function of the MvML is formulated in the large margin learning framework via pairwise constraints, under which the distance of each similar pair is smaller than that of each dissimilar pair by a margin. Moreover, to exploit the nonlinear structure of data points, we extend MvML to a sharable and individual multi-view deep metric learning (MvDML) method by utilizing the neural network architecture to seek multiple nonlinear transformations. Experimental results on face verification, kinship verification, and person re-identification show the effectiveness of the proposed sharable and individual multi-view metric learning methods.

A Machine Learning Approach for Visual Recognition of Complex Parts in Robotic Manipulation

This research presents a method for the visual recognition of parts using machine learning services to enable the manipulation of complex parts. Robotic manipulation of complex parts is a challenging application due to the uncertainty of the parts’ positioning as well as the gripper's grasping instability. This instability is caused by the non-symmetrical and complex geometries that may result in a slightly variable orientation of the part after being grasped, which is outside the handling/assembly process tolerance.To compensate for this, a visual recognition approach is implemented via classifiers. Finally, a case study focusing on the manipulation of consumer goods is demonstrated and evaluated.