Analysis of activation maps through global pooling measurements for texture classification

Condori, Rayner H. Montes; Bruno, Odemir Martinez

doi:10.1016/j.ins.2020.09.058

Cited by 12 publications

(17 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The A (l) measurements then become the inputs to an FC layer. In [20], these pooling measurements were transformed into feature vectors. Two global pooling measurements are used for feature extraction in the experiments presented here: global entropy pooling (GEP) and global mean thresholding pooling (GMTP).…”

Section: Global Pooling Measurementsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Features for Training Support Vector Machines

2021

View full text Add to dashboard Cite

Features play a crucial role in computer vision. Initially designed to detect salient elements by means of handcrafted algorithms, features now are often learned using different layers in convolutional neural networks (CNNs). This paper develops a generic computer vision system based on features extracted from trained CNNs. Multiple learned features are combined into a single structure to work on different image classification tasks. The proposed system was derived by testing several approaches for extracting features from the inner layers of CNNs and using them as inputs to support vector machines that are then combined by sum rule. Several dimensionality reduction techniques were tested for reducing the high dimensionality of the inner layers so that they can work with SVMs. The empirically derived generic vision system based on applying a discrete cosine transform (DCT) separately to each channel is shown to significantly boost the performance of standard CNNs across a large and diverse collection of image data sets. In addition, an ensemble of different topologies taking the same DCT approach and combined with global mean thresholding pooling obtained state-of-the-art results on a benchmark image virus data set.

show abstract

Section: Global Pooling Measurementsmentioning

confidence: 99%

“…In [19], features were extracted from the penultimate layers of pretrained CNNs and merged with the outputs of the deep layers and CNN scores. Finally, in [20], features were investigated layer by layer and were discovered to provide quality information about the texture of images at multiple depths.…”

Section: Introductionmentioning

confidence: 99%

Deep Features for Training Support Vector Machines

2021

View full text Add to dashboard Cite

show abstract

“…Additionally, we used PyTorch 1.0 (PASZKE et al, 2017) to import the pre-trained weights for BN-VGG-19 and INCEPTION-V3, and we used Keras (CHOLLET et al, 2015) to import the pre-trained weights for RESNET-50. Source: Adapted from M. Condori and Bruno (2021).…”

Section: Target Task Datasets and Pre-trained Modelsmentioning

confidence: 99%

“…Indeed, Cui et al (2018) have shown that measuring the similarity between the source domain and the target domain is crucial for fine-tuning TL methods since it could determine beforehand whether good results are possible in the target domain. Source: Adapted from M. Condori and Bruno (2021).…”

Section: Performance Of Gap Features Across Multiple Depth Levelsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-layer analysis of convolutional neural networks for transfer learning applications

Condori¹

View full text Add to dashboard Cite

Deep learning has become a hot topic in artificial intelligence due to its ability to model complex concepts from simple ones. In this regard, the convolutional neural network (CNN) is one of the most popular kinds of neural networks currently used in computer vision and related areas. In general, the following factors contributed to its popularity. (i) With enough data, most CNNs can be trained from scratch and learn powerful representations that solve the task at stake. (ii) On the other hand, with a limited volume of data, it is possible to also learn powerful representations by adapting the knowledge of a pre-trained CNN model via a transfer learning strategy. As a result, CNNs have advanced the state-of-the-art in many visual recognition tasks, leading to numerous applications in various fields outside of computer science, such as medicine and biology. Nevertheless, many of the best research efforts are focused on improving the state-of-the-art on a few datasets, such as ImageNet for image classification and COCO for object detection. On the other hand, research progress in many other domains is reduced to blindly applying existing approaches or re-inventing everything from scratch, resulting in the development of flawed methods in both cases. Therefore, this thesis focuses on understanding through systematic experiments why and when a pre-trained CNN model underperforms on a given task, to propose suitable solutions. In the first part of our study, we examined the task of texture recognition and discovered that all previous studies tended to focus exclusively on category-based texture datasets, leading to the misconception that only the deepest layers had the texture information needed to solve that task. We then show, by proposing multilayer transfer learning strategies, that the contribution of shallow layers is not trivial and should be used in certain applications. In the second part of our study, we focus on challenging object detection tasks (pollen grain detection and stomata localization), where we observe a situation similar to that of texture recognition. Therefore, in both cases, we also applied multilayer analysis to propose fast single-stage detectors that can handle large images accurately and efficiently.

show abstract