paper-with-me

홈 › Papers

Investigating the Robustness of Vision Transformers against Label Noise in Medical Image Classification

2024-02-26 · Bidur Khanal, Prashant Shrestha, Sanskar Amgain, Bishesh Khanal, Binod Bhattarai, Cristian A. Linte

Label noise in medical image classification datasets significantly hampers the training of supervised deep learning methods, undermining their generalizability. The test performance of a model tends to decrease as the label noise rate increases. Over recent years, several methods have been proposed to mitigate the impact of label noise in medical image classification and enhance the robustness of the model. Predominantly, these works have employed CNN-based architectures as the backbone of their classifiers for feature extraction. However, in recent years, Vision Transformer (ViT)-based backbones have replaced CNNs, demonstrating improved performance and a greater ability to learn more generalizable features, especially when the dataset is large. Nevertheless, no prior work has rigorously investigated how transformer-based backbones handle the impact of label noise in medical image classification. In this paper, we investigate the architectural robustness of ViT against label noise and compare it to that of CNNs. We use two medical image classification datasets -- COVID-DU-Ex, and NCT-CRC-HE-100K -- both corrupted by injecting label noise at various rates. Additionally, we show that pretraining is crucial for ensuring ViT's improved robustness against label noise in supervised training.

📄 PDF Abstract BibTeX arXiv:2402.16734

Code (0)

등록된 구현이 없습니다.

Tasks

Classificationimage-classificationImage ClassificationMedical Image Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Adam 설명 없음
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Exploring the Robustness of In-Context Learning with Noisy Labels

2024-04-28 · Chen Cheng, Xinzhi Yu, Haodong Wen, Jingsong Sun 외

Recently, the mysterious In-Context Learning (ICL) ability exhibited by Transformer architectures, especially in large language models (LLMs), has sparked significant research interest. However, the resilience of Transfo…

Data AugmentationIn-Context LearningLearning with noisy labels

Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers

2025-02-07 · Chashi Mahiul Islam, Samuel Jacob Chacko, Mao Nishino, Xiuwen Liu

While transformer-based models dominate NLP and vision applications, their underlying mechanisms to map the input space to the label space semantically are not well understood. In this paper, we study the sources of know…

Zero-shot Generalization

[Re] Improving Interpretation Faithfulness for Vision Transformers

2025-09-18 · Izabela Kurek, Wojciech Trejter, Stipe Frkovic, Andro Erdelez arxiv

This work aims to reproduce the results of Faithful Vision Transformers (FViTs) proposed by arXiv:2311.17983 alongside interpretability methods for Vision Transformers from arXiv:2012.09838 and Xu (2022) et al. We invest…

Curved Representation Space of Vision Transformers

2022-10-11 · Juyeop Kim, Junha Park, Songkuk Kim, Jong-Seok Lee

Neural networks with self-attention (a.k.a. Transformers) like ViT and Swin have emerged as a better alternative to traditional convolutional neural networks (CNNs). However, our understanding of how the new architecture…

Exploring Adversarial Robustness of Vision Transformers in the Spectral Perspective

2022-08-20 · Gihyun Kim, Juyeop Kim, Jong-Seok Lee

The Vision Transformer has emerged as a powerful tool for image classification tasks, surpassing the performance of convolutional neural networks (CNNs). Recently, many researchers have attempted to understand the robust…

Adversarial Robustnessimage-classificationImage Classification