Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN
- URL: http://arxiv.org/abs/2401.13193v1
- Date: Wed, 24 Jan 2024 02:42:50 GMT
- Title: Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN
- Authors: Minsoo Kang, Minkoo Kang, Suhyun Kim
- Abstract summary: Deep learning models often face challenges related to complexity and overfitting.
One notable concern is that the model often relies heavily on a limited subset of filters for making predictions.
We present a novel method called Catch-up Mix, which provides learning opportunities to a wide range of filters during training.
- Score: 15.3232203753165
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep learning has made significant advances in computer vision, particularly
in image classification tasks. Despite their high accuracy on training data,
deep learning models often face challenges related to complexity and
overfitting. One notable concern is that the model often relies heavily on a
limited subset of filters for making predictions. This dependency can result in
compromised generalization and an increased vulnerability to minor variations.
While regularization techniques like weight decay, dropout, and data
augmentation are commonly used to address this issue, they may not directly
tackle the reliance on specific filters. Our observations reveal that the heavy
reliance problem gets severe when slow-learning filters are deprived of
learning opportunities due to fast-learning filters. Drawing inspiration from
image augmentation research that combats over-reliance on specific image
regions by removing and replacing parts of images, our idea is to mitigate the
problem of over-reliance on strong filters by substituting highly activated
features. To this end, we present a novel method called Catch-up Mix, which
provides learning opportunities to a wide range of filters during training,
focusing on filters that may lag behind. By mixing activation maps with
relatively lower norms, Catch-up Mix promotes the development of more diverse
representations and reduces reliance on a small subset of filters. Experimental
results demonstrate the superiority of our method in various vision
classification datasets, providing enhanced robustness.
Related papers
- Granularity Matters in Long-Tail Learning [62.30734737735273]
We offer a novel perspective on long-tail learning, inspired by an observation: datasets with finer granularity tend to be less affected by data imbalance.
We introduce open-set auxiliary classes that are visually similar to existing ones, aiming to enhance representation learning for both head and tail classes.
To prevent the overwhelming presence of auxiliary classes from disrupting training, we introduce a neighbor-silencing loss.
arXiv Detail & Related papers (2024-10-21T13:06:21Z) - Frequency Dropout: Feature-Level Regularization via Randomized Filtering [24.53978165468098]
Deep convolutional neural networks are susceptible to picking up spurious correlations from the training signal.
We propose a training strategy, Frequency Dropout, to prevent convolutional neural networks from learning frequency-specific imaging features.
Our results suggest that the proposed approach does not only improve predictive accuracy but also improves robustness against domain shift.
arXiv Detail & Related papers (2022-09-20T16:42:21Z) - Patch-wise Contrastive Style Learning for Instagram Filter Removal [3.867363075280544]
Social media filters are one of the most common resources of various corruptions and perturbations for real-world visual analysis applications.
We introduce Contrastive Instagram Filter Removal Network (CIFR), which enhances this idea for Instagram filter removal by employing a novel multi-layer patch-wise contrastive style learning mechanism.
arXiv Detail & Related papers (2022-04-15T14:38:28Z) - Adversarial Robustness through the Lens of Convolutional Filters [2.0305676256390934]
We investigate 3x3 convolution filters that form in adversarially-trained models.
Filters are extracted from 71 public models of the linf-RobustBench CIFAR-10/100 and ImageNet1k leaderboard.
arXiv Detail & Related papers (2022-04-05T20:29:16Z) - Learning Versatile Convolution Filters for Efficient Visual Recognition [125.34595948003745]
This paper introduces versatile filters to construct efficient convolutional neural networks.
We conduct theoretical analysis on network complexity and an efficient convolution scheme is introduced.
Experimental results on benchmark datasets and neural networks demonstrate that our versatile filters are able to achieve comparable accuracy as that of original filters.
arXiv Detail & Related papers (2021-09-20T06:07:14Z) - Content-adaptive Representation Learning for Fast Image Super-resolution [6.5468866820512215]
We adrress the efficiency issue in image SR by incorporating a patch-wise rolling network to content-adaptively recover images according to difficulty levels.
In contrast to existing studies that ignore difficulty diversity, we adopt different stage of a neural network to perform image restoration.
Our model not only shows a significant acceleration but also maintain state-of-the-art performance.
arXiv Detail & Related papers (2021-05-20T10:24:29Z) - Graph Neural Networks with Adaptive Frequency Response Filter [55.626174910206046]
We develop a graph neural network framework AdaGNN with a well-smooth adaptive frequency response filter.
We empirically validate the effectiveness of the proposed framework on various benchmark datasets.
arXiv Detail & Related papers (2021-04-26T19:31:21Z) - Training Interpretable Convolutional Neural Networks by Differentiating
Class-specific Filters [64.46270549587004]
Convolutional neural networks (CNNs) have been successfully used in a range of tasks.
CNNs are often viewed as "black-box" and lack of interpretability.
We propose a novel strategy to train interpretable CNNs by encouraging class-specific filters.
arXiv Detail & Related papers (2020-07-16T09:12:26Z) - Filter Grafting for Deep Neural Networks: Reason, Method, and
Cultivation [86.91324735966766]
Filter is the key component in modern convolutional neural networks (CNNs)
In this paper, we introduce filter grafting (textbfMethod) to achieve this goal.
We develop a novel criterion to measure the information of filters and an adaptive weighting strategy to balance the grafted information among networks.
arXiv Detail & Related papers (2020-04-26T08:36:26Z) - Recognizing Instagram Filtered Images with Feature De-stylization [81.38905784617089]
This paper presents a study on how popular pretrained models are affected by commonly used Instagram filters.
Our analysis suggests that simple structure preserving filters which only alter the global appearance of an image can lead to large differences in the convolutional feature space.
We introduce a lightweight de-stylization module that predicts parameters used for scaling and shifting feature maps to "undo" the changes incurred by filters.
arXiv Detail & Related papers (2019-12-30T16:48:16Z)
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.