When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations

• URL: http://arxiv.org/abs/2106.01548v1
• Date: Thu, 3 Jun 2021 02:08:03 GMT
• Title: When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations
• Authors: Xiangning Chen, Cho-Jui Hsieh, Boqing Gong
• Abstract summary: Vision Transformers (ViTs) and existing VisionNets signal efforts on replacing hand-wired features or inductive throughputs with general-purpose neural architectures. This paper investigates ViTs and Res-Mixers from the lens of loss geometry, intending to improve the models' data efficiency at training and inference. We show that the improved robustness attributes to sparser active neurons in the first few layers. The resultant ViTs outperform Nets of similar size and smoothness when trained from scratch on ImageNet without large-scale pretraining or strong data augmentations.
• Score: 111.44860506703307
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision Transformers (ViTs) and MLPs signal further efforts on replacing hand-wired features or inductive biases with general-purpose neural architectures. Existing works empower the models by massive data, such as large-scale pretraining and/or repeated strong data augmentations, and still report optimization-related problems (e.g., sensitivity to initialization and learning rate). Hence, this paper investigates ViTs and MLP-Mixers from the lens of loss geometry, intending to improve the models' data efficiency at training and generalization at inference. Visualization and Hessian reveal extremely sharp local minima of converged models. By promoting smoothness with a recently proposed sharpness-aware optimizer, we substantially improve the accuracy and robustness of ViTs and MLP-Mixers on various tasks spanning supervised, adversarial, contrastive, and transfer learning (e.g., +5.3\% and +11.0\% top-1 accuracy on ImageNet for ViT-B/16 and Mixer-B/16, respectively, with the simple Inception-style preprocessing). We show that the improved smoothness attributes to sparser active neurons in the first few layers. The resultant ViTs outperform ResNets of similar size and throughput when trained from scratch on ImageNet without large-scale pretraining or strong data augmentations. They also possess more perceptive attention maps.

Related papers

• HSViT: Horizontally Scalable Vision Transformer [16.46308352393693]
  Vision Transformer (ViT) requires pre-training on large-scale datasets to perform well. This paper introduces a novel horizontally scalable vision transformer (HSViT) scheme. HSViT achieves up to 10% higher top-1 accuracy than state-of-the-art schemes on small datasets.
  arXiv  Detail & Related papers  (2024-04-08T04:53:29Z)
• How to Train Vision Transformer on Small-scale Datasets? [4.56717163175988]
  In contrast to convolutional neural networks, Vision Transformer lacks inherent inductive biases. We show that self-supervised inductive biases can be learned directly from small-scale datasets. This allows to train these models without large-scale pre-training, changes to model architecture or loss functions.
  arXiv  Detail & Related papers  (2022-10-13T17:59:19Z)
• Where are my Neighbors? Exploiting Patches Relations in Self-Supervised Vision Transformer [3.158346511479111]
  We propose a simple but still effective self-supervised learning (SSL) strategy to train Vision Transformers (ViTs) We define a set of SSL tasks based on relations of image patches that the model has to solve before or jointly during the downstream training. Our RelViT model optimize all the output tokens of the transformer encoder that are related to the image patches, thus exploiting more training signal at each training step.
  arXiv  Detail & Related papers  (2022-06-01T13:25:32Z)
• Improving Vision Transformers by Revisiting High-frequency Components [106.7140968644414]
  We show that Vision Transformer (ViT) models are less effective in capturing the high-frequency components of images than CNN models. To compensate, we propose HAT, which directly augments high-frequency components of images via adversarial training. We show that HAT can consistently boost the performance of various ViT models.
  arXiv  Detail & Related papers  (2022-04-03T05:16:51Z)
• Bootstrapping ViTs: Towards Liberating Vision Transformers from Pre-training [29.20567759071523]
  Vision Transformers (ViTs) are developing rapidly and starting to challenge the domination of convolutional neural networks (CNNs) in computer vision. This paper introduces CNNs' inductive biases back to ViTs while preserving their network architectures for higher upper bound. Experiments on CIFAR-10/100 and ImageNet-1k with limited training data have shown encouraging results.
  arXiv  Detail & Related papers  (2021-12-07T07:56:50Z)
• Self-Supervised Pre-Training for Transformer-Based Person Re-Identification [54.55281692768765]
  Transformer-based supervised pre-training achieves great performance in person re-identification (ReID) Due to the domain gap between ImageNet and ReID datasets, it usually needs a larger pre-training dataset to boost the performance. This work aims to mitigate the gap between the pre-training and ReID datasets from the perspective of data and model structure.
  arXiv  Detail & Related papers  (2021-11-23T18:59:08Z)
• How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers [74.06040005144382]
  Vision Transformers (ViT) have been shown to attain highly competitive performance for a wide range of vision applications. We conduct a systematic empirical study in order to better understand the interplay between the amount of training data, AugReg, model size and compute budget. We train ViT models of various sizes on the public ImageNet-21k dataset which either match or outperform their counterparts trained on the larger, but not publicly available JFT-300M dataset.
  arXiv  Detail & Related papers  (2021-06-18T17:58:20Z)
• Scaling Vision Transformers [82.08465256393514]
  We study how Vision Transformers scale and characterize the relationships between error rate, data, and compute. We train a ViT model with two billion parameters, which attains a new state-of-the-art on ImageNet of 90.45% top-1 accuracy. The model also performs well on few-shot learning, for example, attaining 84.86% top-1 accuracy on ImageNet with only 10 examples per class.
  arXiv  Detail & Related papers  (2021-06-08T17:47:39Z)
• Vision Transformers are Robust Learners [65.91359312429147]
  We study the robustness of the Vision Transformer (ViT) against common corruptions and perturbations, distribution shifts, and natural adversarial examples. We present analyses that provide both quantitative and qualitative indications to explain why ViTs are indeed more robust learners.
  arXiv  Detail & Related papers  (2021-05-17T02:39:22Z)

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.