Open-source framework for detecting bias and overfitting for large pathology images

• URL: http://arxiv.org/abs/2503.01827v1
• Date: Mon, 03 Mar 2025 18:52:53 GMT
• Title: Open-source framework for detecting bias and overfitting for large pathology images
• Authors: Anders Sildnes, Nikita Shvetsov, Masoud Tafavvoghi, Vi Ngoc-Nha Tran, Kajsa Møllersen, Lill-Tove Rasmussen Busund, Thomas K. Kilvær, Lars Ailo Bongo,
• Abstract summary: Even foundational models that are trained on datasets with billions of data samples may develop shortcuts that lead to overfitting and bias.<n>We propose a generalized, model-agnostic framework to debug deep learning models.<n>Our framework is available as an open-source tool available on GitHub.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Even foundational models that are trained on datasets with billions of data samples may develop shortcuts that lead to overfitting and bias. Shortcuts are non-relevant patterns in data, such as the background color or color intensity. So, to ensure the robustness of deep learning applications, there is a need for methods to detect and remove such shortcuts. Today's model debugging methods are time consuming since they often require customization to fit for a given model architecture in a specific domain. We propose a generalized, model-agnostic framework to debug deep learning models. We focus on the domain of histopathology, which has very large images that require large models - and therefore large computation resources. It can be run on a workstation with a commodity GPU. We demonstrate that our framework can replicate non-image shortcuts that have been found in previous work for self-supervised learning models, and we also identify possible shortcuts in a foundation model. Our easy to use tests contribute to the development of more reliable, accurate, and generalizable models for WSI analysis. Our framework is available as an open-source tool available on github.

Related papers

• Imitating the Functionality of Image-to-Image Models Using a Single Example [24.819964498441635]
  We study the possibility of imitating the functionality of an image-to-image translation model by observing input-output pairs.<n>We find that even a single example typically suffices for learning to imitate the model's functionality.
  arXiv  Detail & Related papers  (2024-06-02T18:30:41Z)
• Domain Bridge: Generative model-based domain forensic for black-box models [20.84645356097581]
  We introduce an enhanced approach to determine not just the general data domain but also its specific attributes. Our approach uses an image embedding model as the encoder and a generative model as the decoder. A key strength of our approach lies in leveraging the expansive dataset, LAION-5B, on which the generative model Stable Diffusion is trained.
  arXiv  Detail & Related papers  (2024-02-07T07:57:43Z)
• Low-resource finetuning of foundation models beats state-of-the-art in histopathology [3.4577420145036375]
  We benchmark the most popular vision foundation models as feature extractors for histopathology data. By finetuning a foundation model on a single GPU for only two hours or three days depending on the dataset, we can match or outperform state-of-the-art feature extractors. This is a considerable shift from the current state, where only few institutions with large amounts of resources and datasets are able to train a feature extractor.
  arXiv  Detail & Related papers  (2024-01-09T18:46:59Z)
• Open World Object Detection in the Era of Foundation Models [53.683963161370585]
  We introduce a new benchmark that includes five real-world application-driven datasets. We introduce a novel method, Foundation Object detection Model for the Open world, or FOMO, which identifies unknown objects based on their shared attributes with the base known objects.
  arXiv  Detail & Related papers  (2023-12-10T03:56:06Z)
• A Simple and Efficient Baseline for Data Attribution on Images [107.12337511216228]
  Current state-of-the-art approaches require a large ensemble of as many as 300,000 models to accurately attribute model predictions. In this work, we focus on a minimalist baseline, utilizing the feature space of a backbone pretrained via self-supervised learning to perform data attribution. Our method is model-agnostic and scales easily to large datasets.
  arXiv  Detail & Related papers  (2023-11-03T17:29:46Z)
• Universal Domain Adaptation from Foundation Models: A Baseline Study [58.51162198585434]
  We make empirical studies of state-of-the-art UniDA methods using foundation models. We introduce textitCLIP distillation, a parameter-free method specifically designed to distill target knowledge from CLIP models. Although simple, our method outperforms previous approaches in most benchmark tasks.
  arXiv  Detail & Related papers  (2023-05-18T16:28:29Z)
• DINOv2: Learning Robust Visual Features without Supervision [75.42921276202522]
  This work shows that existing pretraining methods, especially self-supervised methods, can produce such features if trained on enough curated data from diverse sources. Most of the technical contributions aim at accelerating and stabilizing the training at scale. In terms of data, we propose an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature.
  arXiv  Detail & Related papers  (2023-04-14T15:12:19Z)
• ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing [45.14977000707886]
  Higher accuracy on ImageNet usually leads to better robustness against different corruptions. We create a toolkit for object editing with controls of backgrounds, sizes, positions, and directions. We evaluate the performance of current deep learning models, including both convolutional neural networks and vision transformers.
  arXiv  Detail & Related papers  (2023-03-30T02:02:32Z)
• InvGAN: Invertible GANs [88.58338626299837]
  InvGAN, short for Invertible GAN, successfully embeds real images to the latent space of a high quality generative model. This allows us to perform image inpainting, merging, and online data augmentation.
  arXiv  Detail & Related papers  (2021-12-08T21:39:00Z)
• Top-KAST: Top-K Always Sparse Training [50.05611544535801]
  We propose Top-KAST, a method that preserves constant sparsity throughout training. We show that it performs comparably to or better than previous works when training models on the established ImageNet benchmark. In addition to our ImageNet results, we also demonstrate our approach in the domain of language modeling.
  arXiv  Detail & Related papers  (2021-06-07T11:13:05Z)
• Dynamic transformation of prior knowledge into Bayesian models for data streams [2.294014185517203]
  We consider how to effectively use prior knowledge when learning a Bayesian model from streaming environments where data come infinitely and sequentially. We propose a novel framework that enables to incorporate the prior knowledge of different forms into a base Bayesian model for data streams.
  arXiv  Detail & Related papers  (2020-03-13T05:39:01Z)

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.