Powerful Design of Small Vision Transformer on CIFAR10

• URL: http://arxiv.org/abs/2501.06220v1
• Date: Tue, 07 Jan 2025 00:41:34 GMT
• Title: Powerful Design of Small Vision Transformer on CIFAR10
• Authors: Gent Wu,
• Abstract summary: Vision Transformers (ViTs) have demonstrated remarkable success on large-scale datasets, but their performance on smaller datasets often falls short of CNNs. This paper explores the design and optimization of Tiny ViTs for small datasets, using CIFAR-10 as a benchmark.
• Score: 0.0
• License:
• Abstract: Vision Transformers (ViTs) have demonstrated remarkable success on large-scale datasets, but their performance on smaller datasets often falls short of convolutional neural networks (CNNs). This paper explores the design and optimization of Tiny ViTs for small datasets, using CIFAR-10 as a benchmark. We systematically evaluate the impact of data augmentation, patch token initialization, low-rank compression, and multi-class token strategies on model performance. Our experiments reveal that low-rank compression of queries in Multi-Head Latent Attention (MLA) incurs minimal performance loss, indicating redundancy in ViTs. Additionally, introducing multiple CLS tokens improves global representation capacity, boosting accuracy. These findings provide a comprehensive framework for optimizing Tiny ViTs, offering practical insights for efficient and effective designs. Code is available at https://github.com/erow/PoorViTs.

Related papers

• MSCViT: A Small-size ViT architecture with Multi-Scale Self-Attention Mechanism for Tiny Datasets [3.8601741392210434]
  Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. We present a small-size ViT architecture with multi-scale self-attention mechanism and convolution blocks to model different scales of attention. Our model achieves an accuracy of 84.68% on CIFAR-100 with 14.0M parameters and 2.5 GFLOPs, without pre-training on large datasets.
  arXiv  Detail & Related papers  (2025-01-10T15:18:05Z)
• Structured Initialization for Attention in Vision Transformers [34.374054040300805]
  convolutional neural networks (CNNs) have an architectural inductive bias enabling them to perform well on small-scale problems. We argue that the architectural bias inherent to CNNs can be reinterpreted as an initialization bias within ViT. This insight is significant as it empowers ViTs to perform equally well on small-scale problems while maintaining their flexibility for large-scale applications.
  arXiv  Detail & Related papers  (2024-04-01T14:34:47Z)
• Enhancing Performance of Vision Transformers on Small Datasets through Local Inductive Bias Incorporation [13.056764072568749]
  Vision transformers (ViTs) achieve remarkable performance on large datasets, but tend to perform worse than convolutional neural networks (CNNs) on smaller datasets. We propose a module called Local InFormation Enhancer (LIFE) that extracts patch-level local information and incorporates it into the embeddings used in the self-attention block of ViTs. Our proposed module is memory and efficient, as well as flexible enough to process auxiliary tokens such as the classification and distillation tokens.
  arXiv  Detail & Related papers  (2023-05-15T11:23:18Z)
• GOHSP: A Unified Framework of Graph and Optimization-based Heterogeneous Structured Pruning for Vision Transformer [76.2625311630021]
  Vision transformers (ViTs) have shown very impressive empirical performance in various computer vision tasks. To mitigate this challenging problem, structured pruning is a promising solution to compress model size and enable practical efficiency. We propose GOHSP, a unified framework of Graph and Optimization-based Structured Pruning for ViT models.
  arXiv  Detail & Related papers  (2023-01-13T00:40:24Z)
• A Close Look at Spatial Modeling: From Attention to Convolution [70.5571582194057]
  Vision Transformers have shown great promise recently for many vision tasks due to the insightful architecture design and attention mechanism. We generalize self-attention formulation to abstract a queryirrelevant global context directly and integrate the global context into convolutions. With less than 14M parameters, our FCViT-S12 outperforms related work ResT-Lite by 3.7% top1 accuracy on ImageNet-1K.
  arXiv  Detail & Related papers  (2022-12-23T19:13:43Z)
• 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)
• Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer [56.87383229709899]
  We develop an information rectification module (IRM) and a distribution guided distillation scheme for fully quantized vision transformers (Q-ViT) Our method achieves a much better performance than the prior arts.
  arXiv  Detail & Related papers  (2022-10-13T04:00:29Z)
• Towards Data-Efficient Detection Transformers [77.43470797296906]
  We show most detection transformers suffer from significant performance drops on small-size datasets. We empirically analyze the factors that affect data efficiency, through a step-by-step transition from a data-efficient RCNN variant to the representative DETR. We introduce a simple yet effective label augmentation method to provide richer supervision and improve data efficiency.
  arXiv  Detail & Related papers  (2022-03-17T17:56:34Z)
• Vision Transformer for Small-Size Datasets [23.855575212090365]
  This paper proposes Shifted Patch Tokenization (SPT) and Locality Self-Attention (LSA) SPT and LSA effectively solve the lack of locality inductive bias and enable it to learn from scratch even on small-size datasets. Experimental results show that when both SPT and LSA were applied to the ViTs, the performance improved by an average of 2.96% in Tiny-ImageNet.
  arXiv  Detail & Related papers  (2021-12-27T03:24:03Z)
• When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations [111.44860506703307]
  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.
  arXiv  Detail & Related papers  (2021-06-03T02:08:03Z)
• 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.