scholarly journals Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification

2020 ◽  
Vol 34 (04) ◽  
pp. 6194-6201
Author(s):  
Jing Wang ◽  
Weiqing Min ◽  
Sujuan Hou ◽  
Shengnan Ma ◽  
Yuanjie Zheng ◽  
...  
Keyword(s):  
Image Recognition ◽  
Real World ◽  
Large Scale ◽  
Data Augmentation ◽  
Ground Truth ◽  
Classification Task ◽  
The Real ◽  
Product Recommendation ◽  
Contextual Advertising ◽  
Benchmark Datasets

Logo classification has gained increasing attention for its various applications, such as copyright infringement detection, product recommendation and contextual advertising. Compared with other types of object images, the real-world logo images have larger variety in logo appearance and more complexity in their background. Therefore, recognizing the logo from images is challenging. To support efforts towards scalable logo classification task, we have curated a dataset, Logo-2K+, a new large-scale publicly available real-world logo dataset with 2,341 categories and 167,140 images. Compared with existing popular logo datasets, such as FlickrLogos-32 and LOGO-Net, Logo-2K+ has more comprehensive coverage of logo categories and larger quantity of logo images. Moreover, we propose a Discriminative Region Navigation and Augmentation Network (DRNA-Net), which is capable of discovering more informative logo regions and augmenting these image regions for logo classification. DRNA-Net consists of four sub-networks: the navigator sub-network first selected informative logo-relevant regions guided by the teacher sub-network, which can evaluate its confidence belonging to the ground-truth logo class. The data augmentation sub-network then augments the selected regions via both region cropping and region dropping. Finally, the scrutinizer sub-network fuses features from augmented regions and the whole image for logo classification. Comprehensive experiments on Logo-2K+ and other three existing benchmark datasets demonstrate the effectiveness of proposed method. Logo-2K+ and the proposed strong baseline DRNA-Net are expected to further the development of scalable logo image recognition, and the Logo-2K+ dataset can be found at https://github.com/msn199959/Logo-2k-plus-Dataset.

scholarly journals Edge-assisted Collaborative Image Recognition for Mobile Augmented Reality

2022 ◽  
Vol 18 (1) ◽  
pp. 1-31
Author(s):  
Guohao Lan ◽  
Zida Liu ◽  
Yunfan Zhang ◽  
Tim Scargill ◽  
Jovan Stojkovic ◽  
...  
Keyword(s):  
Augmented Reality ◽  
Image Recognition ◽  
Large Scale ◽  
Data Augmentation ◽  
Recognition Accuracy ◽  
Image Distortion ◽  
Mobile Augmented Reality ◽  
The Real ◽  
In The Wild ◽  
Mobile Ar

Mobile Augmented Reality (AR), which overlays digital content on the real-world scenes surrounding a user, is bringing immersive interactive experiences where the real and virtual worlds are tightly coupled. To enable seamless and precise AR experiences, an image recognition system that can accurately recognize the object in the camera view with low system latency is required. However, due to the pervasiveness and severity of image distortions, an effective and robust image recognition solution for “in the wild” mobile AR is still elusive. In this article, we present CollabAR, an edge-assisted system that provides distortion-tolerant image recognition for mobile AR with imperceptible system latency . CollabAR incorporates both distortion-tolerant and collaborative image recognition modules in its design. The former enables distortion-adaptive image recognition to improve the robustness against image distortions, while the latter exploits the spatial-temporal correlation among mobile AR users to improve recognition accuracy. Moreover, as it is difficult to collect a large-scale image distortion dataset, we propose a Cycle-Consistent Generative Adversarial Network-based data augmentation method to synthesize realistic image distortion. Our evaluation demonstrates that CollabAR achieves over 85% recognition accuracy for “in the wild” images with severe distortions, while reducing the end-to-end system latency to as low as 18.2 ms.

scholarly journals City brain: practice of large‐scale artificial intelligence in the real world

2019 ◽  
Vol 1 (1) ◽  
pp. 28-37 ◽  
Author(s):  
Jianfeng Zhang ◽  
Xian‐Sheng Hua ◽  
Jianqiang Huang ◽  
Xu Shen ◽  
Jingyuan Chen ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Real World ◽  
Large Scale ◽  
The Real

The ontogeny of a mammalian cognitive map in the real world

Science ◽  
2020 ◽  
Vol 369 (6500) ◽  
pp. 194-197 ◽  
Author(s):  
Lee Harten ◽  
Amitay Katz ◽  
Aya Goldshtein ◽  
Michal Handel ◽  
Yossi Yovel
Keyword(s):  
Real World ◽  
Large Scale ◽  
Cognitive Maps ◽  
Cognitive Map ◽  
Interindividual Differences ◽  
The Real ◽  
Fruit Bat ◽  
Wild Fruit ◽  
In The Wild

How animals navigate over large-scale environments remains a riddle. Specifically, it is debated whether animals have cognitive maps. The hallmark of map-based navigation is the ability to perform shortcuts, i.e., to move in direct but novel routes. When tracking an animal in the wild, it is extremely difficult to determine whether a movement is truly novel because the animal’s past movement is unknown. We overcame this difficulty by continuously tracking wild fruit bat pups from their very first flight outdoors and over the first months of their lives. Bats performed truly original shortcuts, supporting the hypothesis that they can perform large-scale map-based navigation. We documented how young pups developed their visual-based map, exemplifying the importance of exploration and demonstrating interindividual differences.

scholarly journals Attention-Aware Adversarial Network for Person Re-Identification

2019 ◽  
Vol 9 (8) ◽  
pp. 1550 ◽  
Author(s):  
Aihong Shen ◽  
Huasheng Wang ◽  
Junjie Wang ◽  
Hongchen Tan ◽  
Xiuping Liu ◽  
...  
Keyword(s):  
High Performance ◽  
Large Scale ◽  
Data Augmentation ◽  
Fundamental Problem ◽  
Training Data ◽  
Specific Data ◽  
Training Strategy ◽  
Adversarial Network ◽  
Benchmark Datasets ◽  
Adversarial Training

Person re-identification (re-ID) is a fundamental problem in the field of computer vision. The performance of deep learning-based person re-ID models suffers from a lack of training data. In this work, we introduce a novel image-specific data augmentation method on the feature map level to enforce feature diversity in the network. Furthermore, an attention assignment mechanism is proposed to enforce that the person re-ID classifier focuses on nearly all important regions of the input person image. To achieve this, a three-stage framework is proposed. First, a baseline classification network is trained for person re-ID. Second, an attention assignment network is proposed based on the baseline network, in which the attention module learns to suppress the response of the current detected regions and re-assign attentions to other important locations. By this means, multiple important regions for classification are highlighted by the attention map. Finally, the attention map is integrated in the attention-aware adversarial network (AAA-Net), which generates high-performance classification results with an adversarial training strategy. We evaluate the proposed method on two large-scale benchmark datasets, including Market1501 and DukeMTMC-reID. Experimental results show that our algorithm performs favorably against the state-of-the-art methods.

scholarly journals In the Shadow of the Palm: Dispersed Ontologies among Marind, West Papua

2018 ◽  
Vol 33 (4) ◽  
pp. 621-649 ◽  
Author(s):  
Sophie Chao
Keyword(s):  
Real World ◽  
Oil Palm ◽  
Large Scale ◽  
Well Being ◽  
Life Forms ◽  
Human Species ◽  
Multispecies Ethnography ◽  
The Real ◽  
Human Exceptionalism ◽  
West Papua

This article explores how indigenous Marind of West Papua conceptualize the radical socio-environmental transformations wrought by large-scale deforestation and oil palm expansion on their customary lands and forests. Within the ecology of the Marind lifeworld, oil palm constitutes a particular kind of person, endowed with particular agencies and affects. Its unwillingness to participate in symbiotic socialities with other species jeopardizes the well-being of the life forms populating a dynamic multispecies cosmology, including humans. Drawing from ontological theories and the multispecies approach, I show how people in a remote place engage with adverse environmental transformations enacted by an other-than-human actor. Assumptions of human exceptionalism come under question in the context of a vegetal being that is exceptional in its own particular and destructive ways. Arguing for greater attention to other-than-human species that are unloving rather than unloved, I explore the epistemological frictions that arise from combining the anthropology of ontology with multispecies ethnography. I also attend to the implications of these theoretical positions in the real world of advocacy for those struggling in and against growing social and ecological precariousness.

scholarly journals Multiactivation Pooling Method in Convolutional Neural Networks for Image Recognition

2018 ◽  
Vol 2018 ◽  
pp. 1-15 ◽  
Author(s):  
Qi Zhao ◽  
Shuchang Lyu ◽  
Boxue Zhang ◽  
Wenquan Feng
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Big Data ◽  
Convolutional Neural Networks ◽  
Image Recognition ◽  
Large Scale ◽  
Fog Computing ◽  
Feature Extractor ◽  
Benchmark Datasets ◽  
Classification Tasks

Convolutional neural networks (CNNs) are becoming more and more popular today. CNNs now have become a popular feature extractor applying to image processing, big data processing, fog computing, etc. CNNs usually consist of several basic units like convolutional unit, pooling unit, activation unit, and so on. In CNNs, conventional pooling methods refer to 2×2 max-pooling and average-pooling, which are applied after the convolutional or ReLU layers. In this paper, we propose a Multiactivation Pooling (MAP) Method to make the CNNs more accurate on classification tasks without increasing depth and trainable parameters. We add more convolutional layers before one pooling layer and expand the pooling region to 4×4, 8×8, 16×16, and even larger. When doing large-scale subsampling, we pick top-k activation, sum up them, and constrain them by a hyperparameter σ. We pick VGG, ALL-CNN, and DenseNets as our baseline models and evaluate our proposed MAP method on benchmark datasets: CIFAR-10, CIFAR-100, SVHN, and ImageNet. The classification results are competitive.

Accurate Image Retrieval With Unsupervised 2-Stage k-NN Re-Ranking

2018 ◽  
pp. 1726-1745
Author(s):  
Dawei Li ◽  
Mooi Choo Chuah
Keyword(s):  
Image Retrieval ◽  
Large Scale ◽  
Ground Truth ◽  
Confidence Score ◽  
Image Feature ◽  
Superior Performance ◽  
Ranking Algorithm ◽  
Ranking List ◽  
Image Patches ◽  
Benchmark Datasets

Many state-of-the-art image retrieval systems include a re-ranking step to refine the suggested initial ranking list so as to improve the retrieval accuracy. In this paper, we present a novel 2-stage k-NN re-ranking algorithm. In stage one, we generate an expanded list of candidate database images for re-ranking so that lower ranked ground truth images will be included and re-ranked. In stage two, we re-rank the list of candidate images using a confidence score which is calculated based on, rRBO, a new proposed ranking list similarity measure. In addition, we propose the rLoCATe image feature, which captures robust color and texture information on salient image patches, and shows superior performance in the image retrieval task. We evaluate the proposed re-ranking algorithm on various initial ranking lists created using both SIFT and rLoCATe on two popular benchmark datasets along with a large-scale one million distraction dataset. The results show that our proposed algorithm is not sensitive for different parameter configurations and it outperforms existing k-NN re-ranking methods.

scholarly journals Smart Black Box 2.0: Efficient High-Bandwidth Driving Data Collection Based on Video Anomalies

Algorithms ◽  
2021 ◽  
Vol 14 (2) ◽  
pp. 57
Author(s):  
Ryan Feng ◽  
Yu Yao ◽  
Ella Atkins
Keyword(s):  
Data Collection ◽  
Real World ◽  
Autonomous Vehicles ◽  
Ground Truth ◽  
Black Box ◽  
Video Data ◽  
Detection Methods ◽  
Real World Data ◽  
The Real ◽  
High Bandwidth

Autonomous vehicles require fleet-wide data collection for continuous algorithm development and validation. The smart black box (SBB) intelligent event data recorder has been proposed as a system for prioritized high-bandwidth data capture. This paper extends the SBB by applying anomaly detection and action detection methods for generalized event-of-interest (EOI) detection. An updated SBB pipeline is proposed for the real-time capture of driving video data. A video dataset is constructed to evaluate the SBB on real-world data for the first time. SBB performance is assessed by comparing the compression of normal and anomalous data and by comparing our prioritized data recording with an FIFO strategy. The results show that SBB data compression can increase the anomalous-to-normal memory ratio by ∼25%, while the prioritized recording strategy increases the anomalous-to-normal count ratio when compared to an FIFO strategy. We compare the real-world dataset SBB results to a baseline SBB given ground-truth anomaly labels and conclude that improved general EOI detection methods will greatly improve SBB performance.

Sign in / Sign up

Export Citation Format

Share Document