Improving the Resolution of CNN Feature Maps Efficiently with
Multisampling
- URL: http://arxiv.org/abs/1805.10766v2
- Date: Sun, 10 Sep 2023 23:04:24 GMT
- Title: Improving the Resolution of CNN Feature Maps Efficiently with
Multisampling
- Authors: Shayan Sadigh, Pradeep Sen
- Abstract summary: One version of our method, which we call subsampling, significantly improves the accuracy of state-of-the-art architectures such as DenseNet and ResNet without any additional parameters.
We glean possible insight into the nature of data augmentations and demonstrate experimentally that coarse feature maps are bottlenecking the performance of neural networks in image classification.
- Score: 8.655380837944188
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We describe a new class of subsampling techniques for CNNs, termed
multisampling, that significantly increases the amount of information kept by
feature maps through subsampling layers. One version of our method, which we
call checkered subsampling, significantly improves the accuracy of
state-of-the-art architectures such as DenseNet and ResNet without any
additional parameters and, remarkably, improves the accuracy of certain
pretrained ImageNet models without any training or fine-tuning. We glean
possible insight into the nature of data augmentations and demonstrate
experimentally that coarse feature maps are bottlenecking the performance of
neural networks in image classification.
Related papers
- Distance Weighted Trans Network for Image Completion [52.318730994423106]
We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components.
CNNs are used to augment the local texture information of coarse priors.
DWT blocks are used to recover certain coarse textures and coherent visual structures.
arXiv Detail & Related papers (2023-10-11T12:46:11Z) - Content-Adaptive Downsampling in Convolutional Neural Networks [15.073405675079558]
Many convolutional neural networks (CNNs) rely on progressive downsampling of their feature maps to increase the network's receptive field and decrease computational cost.
This comes at the price of losing granularity in the feature maps, limiting the ability to correctly understand images or recover fine detail in dense prediction tasks.
We propose an adaptive downsampling scheme that generalizes the above idea by allowing to process informative regions at a higher resolution than less informative ones.
arXiv Detail & Related papers (2023-05-16T14:58:30Z) - SDWNet: A Straight Dilated Network with Wavelet Transformation for Image
Deblurring [23.86692375792203]
Image deblurring is a computer vision problem that aims to recover a sharp image from a blurred image.
Our model uses dilated convolution to enable the obtainment of the large receptive field with high spatial resolution.
We propose a novel module using the wavelet transform, which effectively helps the network to recover clear high-frequency texture details.
arXiv Detail & Related papers (2021-10-12T07:58:10Z) - The Mind's Eye: Visualizing Class-Agnostic Features of CNNs [92.39082696657874]
We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most informative features of a specific layer.
Our method uses a dual-objective activation and distance loss, without requiring a generator network nor modifications to the original model.
arXiv Detail & Related papers (2021-01-29T07:46:39Z) - Fusion of CNNs and statistical indicators to improve image
classification [65.51757376525798]
Convolutional Networks have dominated the field of computer vision for the last ten years.
Main strategy to prolong this trend relies on further upscaling networks in size.
We hypothesise that adding heterogeneous sources of information may be more cost-effective to a CNN than building a bigger network.
arXiv Detail & Related papers (2020-12-20T23:24:31Z) - Interpretable Detail-Fidelity Attention Network for Single Image
Super-Resolution [89.1947690981471]
We propose a purposeful and interpretable detail-fidelity attention network to progressively process smoothes and details in divide-and-conquer manner.
Particularly, we propose a Hessian filtering for interpretable feature representation which is high-profile for detail inference.
Experiments demonstrate that the proposed methods achieve superior performances over the state-of-the-art methods.
arXiv Detail & Related papers (2020-09-28T08:31:23Z) - Adaptive Exploitation of Pre-trained Deep Convolutional Neural Networks
for Robust Visual Tracking [14.627458410954628]
This paper provides a comprehensive analysis of four commonly used CNN models to determine the best feature maps of each model.
With the aid of analysis results as attribute dictionaries, adaptive exploitation of deep features is proposed to improve the accuracy and robustness of visual trackers.
arXiv Detail & Related papers (2020-08-29T17:09:43Z) - Learning Enriched Features for Real Image Restoration and Enhancement [166.17296369600774]
convolutional neural networks (CNNs) have achieved dramatic improvements over conventional approaches for image restoration task.
We present a novel architecture with the collective goals of maintaining spatially-precise high-resolution representations through the entire network.
Our approach learns an enriched set of features that combines contextual information from multiple scales, while simultaneously preserving the high-resolution spatial details.
arXiv Detail & Related papers (2020-03-15T11:04:30Z) - Curriculum By Smoothing [52.08553521577014]
Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation.
We propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters.
As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data.
arXiv Detail & Related papers (2020-03-03T07:27:44Z) - Impact of ImageNet Model Selection on Domain Adaptation [26.016647703500883]
We investigate how different ImageNet models affect transfer accuracy on domain adaptation problems.
A higher accuracy ImageNet model produces better features, and leads to higher accuracy on domain adaptation problems.
We also examine the architecture of each neural network to find the best layer for feature extraction.
arXiv Detail & Related papers (2020-02-06T23:58:23Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.