The Counterattack of CNNs in Self-Supervised Learning: Larger Kernel Size might be All You Need

• URL: http://arxiv.org/abs/2312.05695v2
• Date: Tue, 12 Dec 2023 18:23:42 GMT
• Title: The Counterattack of CNNs in Self-Supervised Learning: Larger Kernel Size might be All You Need
• Authors: Tianjin Huang, Tianlong Chen, Zhangyang Wang and Shiwei Liu
• Abstract summary: Vision Transformers have been rapidly uprising in computer vision thanks to their outstanding scaling trends, and gradually replacing convolutional neural networks (CNNs) Recent works on self-supervised learning (SSL) introduce siamese pre-training tasks. People come to believe that Transformers or self-attention modules are inherently more suitable than CNNs in the context of SSL.
• Score: 103.31261028244782
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Transformers have been rapidly uprising in computer vision thanks to their outstanding scaling trends, and gradually replacing convolutional neural networks (CNNs). Recent works on self-supervised learning (SSL) introduce siamese pre-training tasks, on which Transformer backbones continue to demonstrate ever stronger results than CNNs. People come to believe that Transformers or self-attention modules are inherently more suitable than CNNs in the context of SSL. However, it is noteworthy that most if not all prior arts of SSL with CNNs chose the standard ResNets as their backbones, whose architecture effectiveness is known to already lag behind advanced Vision Transformers. Therefore, it remains unclear whether the self-attention operation is crucial for the recent advances in SSL - or CNNs can deliver the same excellence with more advanced designs, too? Can we close the SSL performance gap between Transformers and CNNs? To answer these intriguing questions, we apply self-supervised pre-training to the recently proposed, stronger lager-kernel CNN architecture and conduct an apple-to-apple comparison with Transformers, in their SSL performance. Our results show that we are able to build pure CNN SSL architectures that perform on par with or better than the best SSL-trained Transformers, by just scaling up convolutional kernel sizes besides other small tweaks. Impressively, when transferring to the downstream tasks \texttt{MS COCO} detection and segmentation, our SSL pre-trained CNN model (trained in 100 epochs) achieves the same good performance as the 300-epoch pre-trained Transformer counterpart. We hope this work can help to better understand what is essential (or not) for self-supervised learning backbones.

Related papers

• OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation [70.17681136234202]
  We reexamine the design distinctions and test the limits of what a sparse CNN can achieve. We propose two key components, i.e., adaptive receptive fields (spatially) and adaptive relation, to bridge the gap. This exploration led to the creation of Omni-Adaptive 3D CNNs (OA-CNNs), a family of networks that integrates a lightweight module.
  arXiv  Detail & Related papers  (2024-03-21T14:06:38Z)
• InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions [95.94629864981091]
  This work presents a new large-scale CNN-based foundation model, termed InternImage, which can obtain the gain from increasing parameters and training data like ViTs. The proposed InternImage reduces the strict inductive bias of traditional CNNs and makes it possible to learn stronger and more robust patterns with large-scale parameters from massive data like ViTs.
  arXiv  Detail & Related papers  (2022-11-10T18:59:04Z)
• Can CNNs Be More Robust Than Transformers? [29.615791409258804]
  Vision Transformers is shaking the long dominance of Convolutional Neural Networks (CNNs) in image recognition for a decade. Recent research finds that Transformers are inherently more robust than CNNs, regardless of different training setups. It is believed that such superiority of Transformers should largely be credited to their self-attention-like architectures per se.
  arXiv  Detail & Related papers  (2022-06-07T17:17:07Z)
• Are Transformers More Robust Than CNNs? [17.47001041042089]
  We provide the first fair & in-depth comparisons between Transformers and CNNs. CNNs can easily be as robust as Transformers on defending against adversarial attacks. Our ablations suggest such stronger generalization is largely benefited by the Transformer's self-attention-like architectures.
  arXiv  Detail & Related papers  (2021-11-10T00:18:59Z)
• Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block [0.0]
  transformer-based architectures are surpassing the state-of-the-art set by CNN architectures in accuracy but are computationally very expensive to train from scratch. We study it's transfer learning capabilities and compare it with CNNs so that we can understand which architecture is better when applied to real world problems with small data. We find out that transformers-based architectures not only achieve higher accuracy than CNNs but some transformers even achieve this feat with around 4 times lesser number of parameters.
  arXiv  Detail & Related papers  (2021-10-11T13:43:03Z)
• A Battle of Network Structures: An Empirical Study of CNN, Transformer, and MLP [121.35904748477421]
  Convolutional neural networks (CNN) are the dominant deep neural network (DNN) architecture for computer vision. Transformer and multi-layer perceptron (MLP)-based models, such as Vision Transformer and Vision-Mixer, started to lead new trends. In this paper, we conduct empirical studies on these DNN structures and try to understand their respective pros and cons.
  arXiv  Detail & Related papers  (2021-08-30T06:09:02Z)
• Transformed CNNs: recasting pre-trained convolutional layers with self-attention [17.96659165573821]
  Vision Transformers (ViT) have emerged as a powerful alternative to convolutional networks (CNNs) In this work, we explore the idea of reducing the time spent training these layers by initializing them as convolutional layers. With only 50 epochs of fine-tuning, the resulting T-CNNs demonstrate significant performance gains.
  arXiv  Detail & Related papers  (2021-06-10T14:56:10Z)
• Container: Context Aggregation Network [83.12004501984043]
  Recent finding shows that a simple based solution without any traditional convolutional or Transformer components can produce effective visual representations. We present the model (CONText Ion NERtwok), a general-purpose building block for multi-head context aggregation. In contrast to Transformer-based methods that do not scale well to downstream tasks that rely on larger input image resolutions, our efficient network, named modellight, can be employed in object detection and instance segmentation networks.
  arXiv  Detail & Related papers  (2021-06-02T18:09:11Z)
• 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)

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.