RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy

• URL: http://arxiv.org/abs/2309.09563v1
• Date: Mon, 18 Sep 2023 08:16:30 GMT
• Title: RIDE: Self-Supervised Learning of Rotation-Equivariant Keypoint Detection and Invariant Description for Endoscopy
• Authors: Mert Asim Karaoglu, Viktoria Markova, Nassir Navab, Benjamin Busam, and Alexander Ladikos
• Abstract summary: RIDE is a learning-based method for rotation-equivariant detection and invariant description. It is trained in a self-supervised manner on a large curation of endoscopic images. It sets a new state-of-the-art performance on matching and relative pose estimation tasks.
• Score: 83.4885991036141
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Unlike in natural images, in endoscopy there is no clear notion of an up-right camera orientation. Endoscopic videos therefore often contain large rotational motions, which require keypoint detection and description algorithms to be robust to these conditions. While most classical methods achieve rotation-equivariant detection and invariant description by design, many learning-based approaches learn to be robust only up to a certain degree. At the same time learning-based methods under moderate rotations often outperform classical approaches. In order to address this shortcoming, in this paper we propose RIDE, a learning-based method for rotation-equivariant detection and invariant description. Following recent advancements in group-equivariant learning, RIDE models rotation-equivariance implicitly within its architecture. Trained in a self-supervised manner on a large curation of endoscopic images, RIDE requires no manual labeling of training data. We test RIDE in the context of surgical tissue tracking on the SuPeR dataset as well as in the context of relative pose estimation on a repurposed version of the SCARED dataset. In addition we perform explicit studies showing its robustness to large rotations. Our comparison against recent learning-based and classical approaches shows that RIDE sets a new state-of-the-art performance on matching and relative pose estimation tasks and scores competitively on surgical tissue tracking.

Related papers

• Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images [68.42215385041114]
  This paper introduces a novel lightweight multi-level adaptation and comparison framework to repurpose the CLIP model for medical anomaly detection. Our approach integrates multiple residual adapters into the pre-trained visual encoder, enabling a stepwise enhancement of visual features across different levels. Our experiments on medical anomaly detection benchmarks demonstrate that our method significantly surpasses current state-of-the-art models.
  arXiv  Detail & Related papers  (2024-03-19T09:28:19Z)
• Symmetrical Bidirectional Knowledge Alignment for Zero-Shot Sketch-Based Image Retrieval [69.46139774646308]
  This paper studies the problem of zero-shot sketch-based image retrieval (ZS-SBIR) It aims to use sketches from unseen categories as queries to match the images of the same category. We propose a novel Symmetrical Bidirectional Knowledge Alignment for zero-shot sketch-based image retrieval (SBKA)
  arXiv  Detail & Related papers  (2023-12-16T04:50:34Z)
• On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis [58.634791552376235]
  Deep Learning (DL) models have achieved state-of-the-art performance in diagnosing multiple diseases using reconstructed images as input. DL models are sensitive to varying artifacts as it leads to changes in the input data distribution between the training and testing phases. We propose to use other normalization techniques, such as Group Normalization and Layer Normalization, to inject robustness into model performance against varying image artifacts.
  arXiv  Detail & Related papers  (2023-06-23T03:09:03Z)
• Compressed Sensing MRI Reconstruction Regularized by VAEs with Structured Image Covariance [7.544757765701024]
  This paper investigates how generative models, trained on ground-truth images, can be used changesas priors for inverse problems. We utilize variational autoencoders (VAEs) that generate not only an image but also a covariance uncertainty matrix for each image. We compare our proposed learned regularization against other unlearned regularization approaches and unsupervised and supervised deep learning methods.
  arXiv  Detail & Related papers  (2022-10-26T09:51:49Z)
• Self-Supervised Endoscopic Image Key-Points Matching [1.3764085113103222]
  This paper proposes a novel self-supervised approach for endoscopic image matching based on deep learning techniques. Our method outperformed standard hand-crafted local feature descriptors in terms of precision and recall.
  arXiv  Detail & Related papers  (2022-08-24T10:47:21Z)
• PatchNR: Learning from Small Data by Patch Normalizing Flow Regularization [57.37911115888587]
  We introduce a regularizer for the variational modeling of inverse problems in imaging based on normalizing flows. Our regularizer, called patchNR, involves a normalizing flow learned on patches of very few images.
  arXiv  Detail & Related papers  (2022-05-24T12:14:26Z)
• Robust Collaborative Learning of Patch-level and Image-level Annotations for Diabetic Retinopathy Grading from Fundus Image [33.904136933213735]
  We present a robust framework, which collaboratively utilizes patch-level and image-level annotations, for DR severity grading. By an end-to-end optimization, this framework can bi-directionally exchange the fine-grained lesion and image-level grade information. The proposed framework shows better performance than the recent state-of-the-art algorithms and three clinical ophthalmologists with over nine years of experience.
  arXiv  Detail & Related papers  (2020-08-03T02:17:42Z)
• Towards Unsupervised Learning for Instrument Segmentation in Robotic Surgery with Cycle-Consistent Adversarial Networks [54.00217496410142]
  We propose an unpaired image-to-image translation where the goal is to learn the mapping between an input endoscopic image and a corresponding annotation. Our approach allows to train image segmentation models without the need to acquire expensive annotations. We test our proposed method on Endovis 2017 challenge dataset and show that it is competitive with supervised segmentation methods.
  arXiv  Detail & Related papers  (2020-07-09T01:39:39Z)
• Autoencoders for Unsupervised Anomaly Segmentation in Brain MR Images: A Comparative Study [43.26668942258135]
  New approaches in the field of Unsupervised Anomaly Detection (UAD) in brain MRI. Main principle behind these works is to learn a model of normal anatomy by learning to compress and recover healthy data. concept is of great interest to the medical image analysis community as it i) relieves from the need of vast amounts of manually segmented training data.
  arXiv  Detail & Related papers  (2020-04-07T11:12:07Z)
• Roto-Translation Equivariant Convolutional Networks: Application to Histopathology Image Analysis [11.568329857588099]
  We propose a framework to encode the geometric structure of the special Euclidean motion group SE(2) in convolutional networks. We show that consistent increase of performances can be achieved when using the proposed framework.
  arXiv  Detail & Related papers  (2020-02-20T13:44:29Z)

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.