Results 11 to 20 of about 949,168 (327)
Discriminative Shape Feature Pooling in Deep Neural Networks [PDF]
Journal of Imaging, 2022 Although deep learning approaches are able to generate generic image features from massive labeled data, discriminative handcrafted features still have advantages in providing explicit domain knowledge and reflecting intuitive visual understanding.
Gang Hu, Chahna Dixit, Guanqiu Qi
openalex +4 more sources
Feature fusion network based on strip pooling [PDF]
Scientific Reports, 2021 AbstractContextual information is a key factor affecting semantic segmentation. Recently, many methods have tried to use the self-attention mechanism to capture more contextual information. However, these methods with self-attention mechanism need a huge computation.
Gaihua Wang, Qianyu Zhai
openalex +4 more sources
TI-POOLING: transformation-invariant pooling for feature learning in\n Convolutional Neural Networks [PDF]
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016 In this paper we present a deep neural network topology that incorporates a simple to implement transformation invariant pooling operator (TI-POOLING). This operator is able to efficiently handle prior knowledge on nuisance variations in the data, such as rotation or scale changes.
Д. Н. Лаптев +3 more
+6 more sources
Differentiable Pooling for Hierarchical Feature Learning [PDF]
, 2012 We introduce a parametric form of pooling, based on a Gaussian, which can be optimized alongside the features in a single global objective function. By contrast, existing pooling schemes are based on heuristics (e.g. local maximum) and have no clear link to the cost function of the model.
Matthew D. Zeiler, Rob Fergus
openalex +3 more sources
FEATURE DESCRIPTOR BY CONVOLUTION AND POOLING AUTOENCODERS [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2015 Abstract. In this paper we present several descriptors for feature-based matching based on autoencoders, and we evaluate the performance of these descriptors. In a training phase, we learn autoencoders from image patches extracted in local windows surrounding key points determined by the Difference of Gaussian extractor.
Liuhong Chen +2 more
openalex +4 more sources
Advanced Feature Learning on Point Clouds using Multi-resolution Features and Learnable Pooling [PDF]
Remote Sensing, 2022 Existing point cloud feature learning networks often learn high-semantic point features representing the global context by incorporating sampling, neighborhood grouping, neighborhood-wise feature learning, and feature aggregation. However, this process may result in a substantial loss of granular information due to the sampling operation and the widely-
Kevin Tirta Wijaya +2 more
openalex +5 more sources
Fast Feature Extraction with CNNs with Pooling Layers [PDF]
, 2018 In recent years, many publications showed that convolutional neural network based features can have a superior performance to engineered features. However, not much effort was taken so far to extract local features efficiently for a whole image. In this paper, we present an approach to compute patch-based local feature descriptors efficiently in ...
Christian Bailer +3 more
openalex +3 more sources
Pooling-Invariant Image Feature Learning [PDF]
, 2013 Unsupervised dictionary learning has been a key component in state-of-the-art computer vision recognition architectures. While highly effective methods exist for patch-based dictionary learning, these methods may learn redundant features after the pooling stage in a given early vision architecture.
Yangqing Jia +2 more
openalex +3 more sources
Bregman pooling: feature-space local pooling for image classification [PDF]
International Journal of Multimedia Information Retrieval, 2015 In this paper, we propose a novel feature-space local pooling method for the commonly adopted architecture of image classification. While existing methods partition the feature space based on visual appearance to obtain pooling bins, learning more accurate space partitioning that takes semantics into account boosts performance even for a smaller number
Najjar, Alameen +2 more
openaire +2 more sources
Pooled motion features for first-person videos [PDF]
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015 In this paper, we present a new feature representation for first-person videos. In first-person video understanding (e.g., activity recognition), it is very important to capture both entire scene dynamics (i.e., egomotion) and salient local motion observed in videos. We describe a representation framework based on time series pooling, which is designed
Ryoo, M. S. +2 more
openaire +2 more sources