NCDD: Nearest Centroid Distance Deficit for Out-Of-Distribution Detection in Gastrointestinal Vision

• URL: http://arxiv.org/abs/2412.01590v1
• Date: Mon, 02 Dec 2024 15:07:55 GMT
• Title: NCDD: Nearest Centroid Distance Deficit for Out-Of-Distribution Detection in Gastrointestinal Vision
• Authors: Sandesh Pokhrel, Sanjay Bhandari, Sharib Ali, Tryphon Lambrou, Anh Nguyen, Yash Raj Shrestha, Angus Watson, Danail Stoyanov, Prashnna Gyawali, Binod Bhattarai,
• Abstract summary: The integration of deep learning tools in gastrointestinal vision holds the potential for significant advancements in diagnosis, treatment, and patient care. A major challenge, however, is these tools' tendency to make overconfident predictions, even when encountering unseen or newly emerging disease patterns. We propose a novel nearest-centroid distance deficit (NCCD) score in the feature space for gastrointestinal OOD detection.
• Score: 13.349151639789902
• License:
• Abstract: The integration of deep learning tools in gastrointestinal vision holds the potential for significant advancements in diagnosis, treatment, and overall patient care. A major challenge, however, is these tools' tendency to make overconfident predictions, even when encountering unseen or newly emerging disease patterns, undermining their reliability. We address this critical issue of reliability by framing it as an out-of-distribution (OOD) detection problem, where previously unseen and emerging diseases are identified as OOD examples. However, gastrointestinal images pose a unique challenge due to the overlapping feature representations between in- Distribution (ID) and OOD examples. Existing approaches often overlook this characteristic, as they are primarily developed for natural image datasets, where feature distinctions are more apparent. Despite the overlap, we hypothesize that the features of an in-distribution example will cluster closer to the centroids of their ground truth class, resulting in a shorter distance to the nearest centroid. In contrast, OOD examples maintain an equal distance from all class centroids. Based on this observation, we propose a novel nearest-centroid distance deficit (NCCD) score in the feature space for gastrointestinal OOD detection. Evaluations across multiple deep learning architectures and two publicly available benchmarks, Kvasir2 and Gastrovision, demonstrate the effectiveness of our approach compared to several state-of-the-art methods. The code and implementation details are publicly available at: https://github.com/bhattarailab/NCDD

Related papers

• Going Beyond Conventional OOD Detection [0.0]
  Out-of-distribution (OOD) detection is critical to ensure the safe deployment of deep learning models in critical applications. We present a unified Approach to Spurimatious, fine-grained, and Conventional OOD Detection (ASCOOD) Our approach effectively mitigates the impact of spurious correlations and encourages capturing fine-grained attributes.
  arXiv  Detail & Related papers  (2024-11-16T13:04:52Z)
• Towards Within-Class Variation in Alzheimer's Disease Detection from Spontaneous Speech [60.08015780474457]
  Alzheimer's Disease (AD) detection has emerged as a promising research area that employs machine learning classification models. We identify within-class variation as a critical challenge in AD detection: individuals with AD exhibit a spectrum of cognitive impairments. We propose two novel methods: Soft Target Distillation (SoTD) and Instance-level Re-balancing (InRe), targeting two problems respectively.
  arXiv  Detail & Related papers  (2024-09-22T02:06:05Z)
• TTA-OOD: Test-time Augmentation for Improving Out-of-Distribution Detection in Gastrointestinal Vision [6.290783164114315]
  We introduce a test-time augmentation segment into the OOD detection pipeline. This augmentation shifts the pixel space, which translates into a more distinct semantic representation for OOD examples. We evaluate our method against existing state-of-the-art OOD scores.
  arXiv  Detail & Related papers  (2024-07-19T04:50:54Z)
• EAT: Towards Long-Tailed Out-of-Distribution Detection [55.380390767978554]
  This paper addresses the challenging task of long-tailed OOD detection. The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes. We propose two simple ideas: (1) Expanding the in-distribution class space by introducing multiple abstention classes, and (2) Augmenting the context-limited tail classes by overlaying images onto the context-rich OOD data.
  arXiv  Detail & Related papers  (2023-12-14T13:47:13Z)
• From Global to Local: Multi-scale Out-of-distribution Detection [129.37607313927458]
  Out-of-distribution (OOD) detection aims to detect "unknown" data whose labels have not been seen during the in-distribution (ID) training process. Recent progress in representation learning gives rise to distance-based OOD detection. We propose Multi-scale OOD DEtection (MODE), a first framework leveraging both global visual information and local region details.
  arXiv  Detail & Related papers  (2023-08-20T11:56:25Z)
• A Global and Patch-wise Contrastive Loss for Accurate Automated Exudate Detection [12.669734891001667]
  Diabetic retinopathy (DR) is a leading global cause of blindness. Early detection of hard exudates plays a crucial role in identifying DR, which aids in treating diabetes and preventing vision loss. We present a novel supervised contrastive learning framework to optimize hard exudate segmentation.
  arXiv  Detail & Related papers  (2023-02-22T17:39:00Z)
• Relative distance matters for one-shot landmark detection [16.032695993409853]
  We upgrade cascade comparing to detect (CC2D) to version II by incorporating a simple-yet-effective relative distance bias in the training stage. CC2Dv2 is less possible to detect a wrong point far from the correct landmark. We present an open-source, landmark-labeled dataset for the measurement of biomechanical parameters of the lower extremity.
  arXiv  Detail & Related papers  (2022-03-03T12:50:56Z)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification [83.6017225363714]
  deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance. For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming. In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
  arXiv  Detail & Related papers  (2021-02-26T02:29:30Z)
• DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection [53.40028068801092]
  We propose a novel one-stage HOI detection approach based on a new concept called interaction region for the HOI problem. Unlike previous methods, our approach concentrates on the densely sampled interaction regions across different scales for each human-object pair. In order to compensate for the detection flaws of a single interaction region, we introduce a novel voting strategy.
  arXiv  Detail & Related papers  (2020-10-02T13:57:58Z)

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.