DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets

• URL: http://arxiv.org/abs/2404.02900v1
• Date: Wed, 3 Apr 2024 17:58:21 GMT
• Title: DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
• Authors: Harsh Rangwani, Pradipto Mondal, Mayank Mishra, Ashish Ramayee Asokan, R. Venkatesh Babu,
• Abstract summary: Vision Transformer (ViT) has emerged as a prominent architecture for various computer vision tasks. ViT requires a large amount of data for pre-training. We introduce DeiT-LT to tackle the problem of training ViTs from scratch on long-tailed datasets.
• Score: 30.178427266135756
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Transformer (ViT) has emerged as a prominent architecture for various computer vision tasks. In ViT, we divide the input image into patch tokens and process them through a stack of self attention blocks. However, unlike Convolutional Neural Networks (CNN), ViTs simple architecture has no informative inductive bias (e.g., locality,etc. ). Due to this, ViT requires a large amount of data for pre-training. Various data efficient approaches (DeiT) have been proposed to train ViT on balanced datasets effectively. However, limited literature discusses the use of ViT for datasets with long-tailed imbalances. In this work, we introduce DeiT-LT to tackle the problem of training ViTs from scratch on long-tailed datasets. In DeiT-LT, we introduce an efficient and effective way of distillation from CNN via distillation DIST token by using out-of-distribution images and re-weighting the distillation loss to enhance focus on tail classes. This leads to the learning of local CNN-like features in early ViT blocks, improving generalization for tail classes. Further, to mitigate overfitting, we propose distilling from a flat CNN teacher, which leads to learning low-rank generalizable features for DIST tokens across all ViT blocks. With the proposed DeiT-LT scheme, the distillation DIST token becomes an expert on the tail classes, and the classifier CLS token becomes an expert on the head classes. The experts help to effectively learn features corresponding to both the majority and minority classes using a distinct set of tokens within the same ViT architecture. We show the effectiveness of DeiT-LT for training ViT from scratch on datasets ranging from small-scale CIFAR-10 LT to large-scale iNaturalist-2018.

Related papers

• Experts Weights Averaging: A New General Training Scheme for Vision Transformers [57.62386892571636]
  We propose a training scheme for Vision Transformers (ViTs) that achieves performance improvement without increasing inference cost. During training, we replace some Feed-Forward Networks (FFNs) of the ViT with specially designed, more efficient MoEs. After training, we convert each MoE into an FFN by averaging the experts, transforming the model back into original ViT for inference.
  arXiv  Detail & Related papers  (2023-08-11T12:05:12Z)
• AViT: Adapting Vision Transformers for Small Skin Lesion Segmentation Datasets [19.44142290594537]
  AViT is a novel strategy to mitigate ViTs' data-hunger by transferring any pre-trained ViTs to the SLS task. AViT achieves competitive, and at times superior, performance to SOTA but with significantly fewer trainable parameters.
  arXiv  Detail & Related papers  (2023-07-26T01:44:31Z)
• Exploring Efficient Few-shot Adaptation for Vision Transformers [70.91692521825405]
  We propose a novel efficient Transformer Tuning (eTT) method that facilitates finetuning ViTs in the Few-shot Learning tasks. Key novelties come from the newly presented Attentive Prefix Tuning (APT) and Domain Residual Adapter (DRA) We conduct extensive experiments to show the efficacy of our model.
  arXiv  Detail & Related papers  (2023-01-06T08:42:05Z)
• Learning Imbalanced Data with Vision Transformers [17.14790664854141]
  We propose LiVT to train Vision Transformers (ViTs) from scratch only with Long-Tailed (LT) data. With ample and solid evidence, we show that Masked Generative Pretraining (MGP) is more robust than supervised manners. Our Bal-BCE contributes to the quick convergence of ViTs in just a few epochs.
  arXiv  Detail & Related papers  (2022-12-05T04:05:32Z)
• ViT-FOD: A Vision Transformer based Fine-grained Object Discriminator [21.351034332423374]
  We propose a novel ViT based fine-grained object discriminator for Fine-Grained Visual Classification (FGVC) tasks. Besides a ViT backbone, it introduces three novel components, i.e. Attention Patch Combination (APC), Critical Regions Filter (CRF) and Complementary Tokens Integration (CTI) We conduct comprehensive experiments on widely used datasets and the results demonstrate that ViT-FOD is able to achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-03-24T02:34:57Z)
• Self-Promoted Supervision for Few-Shot Transformer [178.52948452353834]
  Self-promoted sUpervisioN (SUN) is a few-shot learning framework for vision transformers (ViTs) SUN pretrains the ViT on the few-shot learning dataset and then uses it to generate individual location-specific supervision for guiding each patch token. Experiments show that SUN using ViTs significantly surpasses other few-shot learning frameworks with ViTs and is the first one that achieves higher performance than those CNN state-of-the-arts.
  arXiv  Detail & Related papers  (2022-03-14T12:53:27Z)
• Auto-scaling Vision Transformers without Training [84.34662535276898]
  We propose As-ViT, an auto-scaling framework for Vision Transformers (ViTs) without training. As-ViT automatically discovers and scales up ViTs in an efficient and principled manner. As a unified framework, As-ViT achieves strong performance on classification and detection.
  arXiv  Detail & Related papers  (2022-02-24T06:30:55Z)
• Self-slimmed Vision Transformer [52.67243496139175]
  Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. We propose a generic self-slimmed learning approach for vanilla ViTs, namely SiT. Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs.
  arXiv  Detail & Related papers  (2021-11-24T16:48:57Z)
• 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.