Curriculum By Smoothing

• URL: http://arxiv.org/abs/2003.01367v5
• Date: Tue, 5 Jan 2021 04:53:44 GMT
• Title: Curriculum By Smoothing
• Authors: Samarth Sinha, Animesh Garg, Hugo Larochelle
• Abstract summary: 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.
• Score: 52.08553521577014
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. Moreover, recent work in Generative Adversarial Networks (GANs) has highlighted the importance of learning by progressively increasing the difficulty of a learning task [26]. When learning a network from scratch, the information propagated within the network during the earlier stages of training can contain distortion artifacts due to noise which can be detrimental to training. In this paper, we propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. We propose to augment the train-ing of CNNs by controlling the amount of high frequency information propagated within the CNNs as training progresses, by convolving the output of a CNN feature map of each layer with a Gaussian kernel. By decreasing the variance of the Gaussian kernel, we gradually increase the amount of high-frequency information available within the network for inference. As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data. Our proposed augmented training scheme significantly improves the performance of CNNs on various vision tasks without either adding additional trainable parameters or an auxiliary regularization objective. The generality of our method is demonstrated through empirical performance gains in CNN architectures across four different tasks: transfer learning, cross-task transfer learning, and generative models.

Related papers

• Image edge enhancement for effective image classification [7.470763273994321]
  We propose an edge enhancement-based method to enhance both accuracy and training speed of neural networks. Our approach involves extracting high frequency features, such as edges, from images within the available dataset and fusing them with the original images.
  arXiv  Detail & Related papers  (2024-01-13T10:01:34Z)
• Transferability of Convolutional Neural Networks in Stationary Learning Tasks [96.00428692404354]
  We introduce a novel framework for efficient training of convolutional neural networks (CNNs) for large-scale spatial problems. We show that a CNN trained on small windows of such signals achieves a nearly performance on much larger windows without retraining. Our results show that the CNN is able to tackle problems with many hundreds of agents after being trained with fewer than ten.
  arXiv  Detail & Related papers  (2023-07-21T13:51:45Z)
• Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective [53.999128831324576]
  Graph neural networks (GNNs) have pioneered advancements in graph representation learning. This study investigates the role of graph convolution within the context of feature learning theory.
  arXiv  Detail & Related papers  (2023-06-24T10:21:11Z)
• Target Aware Network Architecture Search and Compression for Efficient Knowledge Transfer [9.434523476406424]
  We propose a two-stage framework called TASCNet which enables efficient knowledge transfer. TASCNet reduces the computational complexity of pre-trained CNNs over the target task by reducing both trainable parameters and FLOPs. Similar to computer vision tasks, we have also conducted experiments on Movie Review Sentiment Analysis task.
  arXiv  Detail & Related papers  (2022-05-12T09:11:00Z)
• Knowledge Distillation Circumvents Nonlinearity for Optical Convolutional Neural Networks [4.683612295430957]
  We propose a Spectral CNN Linear Counterpart (SCLC) network architecture and develop a Knowledge Distillation (KD) approach to circumvent the need for a nonlinearity. We show that the KD approach can achieve performance that easily surpasses the standard linear version of a CNN and could approach the performance of the nonlinear network.
  arXiv  Detail & Related papers  (2021-02-26T06:35:34Z)
• 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)
• Graph-Based Neural Network Models with Multiple Self-Supervised Auxiliary Tasks [79.28094304325116]
  Graph Convolutional Networks are among the most promising approaches for capturing relationships among structured data points. We propose three novel self-supervised auxiliary tasks to train graph-based neural network models in a multi-task fashion.
  arXiv  Detail & Related papers  (2020-11-14T11:09:51Z)
• Collaborative Method for Incremental Learning on Classification and Generation [32.07222897378187]
  We introduce a novel algorithm, Incremental Class Learning with Attribute Sharing (ICLAS), for incremental class learning with deep neural networks. As one of its component, incGAN, can generate images with increased variety compared with the training data. Under challenging environment of data deficiency, ICLAS incrementally trains classification and the generation networks.
  arXiv  Detail & Related papers  (2020-10-29T06:34:53Z)
• Neural networks adapting to datasets: learning network size and topology [77.34726150561087]
  We introduce a flexible setup allowing for a neural network to learn both its size and topology during the course of a gradient-based training. The resulting network has the structure of a graph tailored to the particular learning task and dataset.
  arXiv  Detail & Related papers  (2020-06-22T12:46:44Z)

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.