Filter Learning from Deep Descriptors of a Fully Convolutional Siamese Network for Tracking in Videos.
01 Jan 2020-pp 685-694
TL;DR: Esta proposta apresenta ganhos em comparacao com a proposta original da SiamFC, que foi proposto a combinacao de sinal de descritores em blocos de memorias de longo e de curto prazo, os quais representam a primeira e a mais recente aparencia do objeto, respectivamente.
Abstract: Nos ultimos anos, os avancos em Aprendizado Profundo revolucionaram diversas sub-
areas da Visao Computacional, incluindo o Rastreamento de Objetos Visuais. Um tipo especial
de rede neural profunda, a Rede Neural Siamesa, chamou a atencao da comunidade
especializada em rastreamento. Ela possui baixo custo computacional e alta efi cacia para
comparar a similaridade entre objetos. Atualmente, a comunidade cienti ca atingiu resultados
notaveis ao aplicar tais redes ao problema de Rastreamento de Objetos Visuais.
No entanto, observou-se que limitacoes dessa rede neural impactam negativamente no rastreamento.
Superou-se o problema ao se obter um novo descritor para referencia do objeto
combinando descritores passados fornecidos pelo rastreador. Em particular, foi proposto
a combinacao de sinal de descritores em blocos de memorias de longo e de curto prazo,
os quais representam a primeira e a mais recente aparencia do objeto, respectivamente.
Um descritor nal e gerado a partir desses blocos de memoria, o qual o rastreador usa
como referencia. Este trabalho enfatizou-se na obtencao de um metodo para calcular um
banco de ltros otimizado atraves do uso de um algoritmo genetico. O banco de ltros
e utilizado entao para gerar a saida da memoria de curto prazo. De acordo com experimentos
realizados na base de dados OTB, esta proposta apresenta ganhos em comparacao
com a proposta original da SiamFC. Considerando a metrica area abaixo da curva, ha
ganhos de 7.4% e 3.0% para os gra cos de precisao e sucesso, respectivamente, tornando
este trabalho comparavel a metodos do estato da arte.
References
More filters
Proceedings Article•
03 Dec 2012TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.
73,978 citations
Proceedings Article•
01 Jan 2015TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
49,914 citations
07 Jun 2015
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Abstract: We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
40,257 citations
27 Jun 2016
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Abstract: We present YOLO, a new approach to object detection. Prior work on object detection repurposes classifiers to perform detection. Instead, we frame object detection as a regression problem to spatially separated bounding boxes and associated class probabilities. A single neural network predicts bounding boxes and class probabilities directly from full images in one evaluation. Since the whole detection pipeline is a single network, it can be optimized end-to-end directly on detection performance. Our unified architecture is extremely fast. Our base YOLO model processes images in real-time at 45 frames per second. A smaller version of the network, Fast YOLO, processes an astounding 155 frames per second while still achieving double the mAP of other real-time detectors. Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background. Finally, YOLO learns very general representations of objects. It outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
27,256 citations
Posted Content•
TL;DR: It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation.
Abstract: Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key insight is to build "fully convolutional" networks that take input of arbitrary size and produce correspondingly-sized output with efficient inference and learning. We define and detail the space of fully convolutional networks, explain their application to spatially dense prediction tasks, and draw connections to prior models. We adapt contemporary classification networks (AlexNet, the VGG net, and GoogLeNet) into fully convolutional networks and transfer their learned representations by fine-tuning to the segmentation task. We then define a novel architecture that combines semantic information from a deep, coarse layer with appearance information from a shallow, fine layer to produce accurate and detailed segmentations. Our fully convolutional network achieves state-of-the-art segmentation of PASCAL VOC (20% relative improvement to 62.2% mean IU on 2012), NYUDv2, and SIFT Flow, while inference takes one third of a second for a typical image.
9,803 citations
"Filter Learning from Deep Descripto..." refers methods in this paper
...This process is equivalent to evaluate each atomic patch to compose a feature map a (LONG et al., 2015)....
[...]