اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدTesting Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic Relations
61
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Deep learning models are widely used for image analysis. While they offer high performance in terms of accuracy, people are concerned about if these models inappropriately make inferences using irrelevant features that are not encoded from the target object in a given image. To address the concern, we propose a metamorphic testing approach that assesses if a given inference is made based on irrelevant features. Specifically, we propose two novel metamorphic relations to detect such inappropriate inferences. We applied our approach to 10 image classification models and 10 object detection models, with three large datasets, i.e., ImageNet, COCO, and Pascal VOC. Over 5.3% of the top-5 correct predictions made by the image classification models are subject to inappropriate inferences using irrelevant features. The corresponding rate for the object detection models is over 8.5%. Based on the findings, we further designed a new image generation strategy that can effectively attack existing models. Comparing with a baseline approach, our strategy can double the success rate of attacks.
قيم البحث
اقرأ أيضاً
Active Learning methods create an optimized labeled training set from unlabeled data. We introduce a novel Online Active Deep Learning method for Medical Image Analysis. We extend our MedAL active learning framework to present new results in this pap
er. Our novel sampling method queries the unlabeled examples that maximize the average distance to all training set examples. Our online method enhances performance of its underlying baseline deep network. These novelties contribute significant performance improvements, including improving the models underlying deep network accuracy by 6.30%, using only 25% of the labeled dataset to achieve baseline accuracy, reducing backpropagated images during training by as much as 67%, and demonstrating robustness to class imbalance in binary and multi-class tasks.
We extend first-order model agnostic meta-learning algorithms (including FOMAML and Reptile) to image segmentation, present a novel neural network architecture built for fast learning which we call EfficientLab, and leverage a formal definition of th
e test error of meta-learning algorithms to decrease error on out of distribution tasks. We show state of the art results on the FSS-1000 dataset by meta-training EfficientLab with FOMAML and using Bayesian optimization to infer the optimal test-time adaptation routine hyperparameters. We also construct a small benchmark dataset, FP-k, for the empirical study of how meta-learning systems perform in both few- and many-shot settings. On the FP-k dataset, we show that meta-learned initializations provide value for canonical few-shot image segmentation but their performance is quickly matched by conventional transfer learning with performance being equal beyond 10 labeled examples. Our code, meta-learned model, and the FP-k dataset are available at https://github.com/ml4ai/mliis .
We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or pre-training. The approach leverages
input perturbations commonly used in computer vision tasks to regularize the value function. Existing model-free approaches, such as Soft Actor-Critic (SAC), are not able to train deep networks effectively from image pixels. However, the addition of our augmentation method dramatically improves SACs performance, enabling it to reach state-of-the-art performance on the DeepMind control suite, surpassing model-based (Dreamer, PlaNet, and SLAC) methods and recently proposed contrastive learning (CURL). Our approach can be combined with any model-free reinforcement learning algorithm, requiring only minor modifications. An implementation can be found at https://sites.google.com/view/data-regularized-q.
Despite its best performance in image denoising, the supervised deep denoising methods require paired noise-clean data, which are often unavailable. To address this challenge, Noise2Noise was designed based on the fact that paired noise-clean images
can be replaced by paired noise-noise images that are easier to collect. However, in many scenarios the collection of paired noise-noise images is still impractical. To bypass labeled images, Noise2Void methods predict masked pixels from their surroundings with single noisy images only and give improved denoising results that still need improvements. An observation on classic denoising methods is that non-local mean (NLM) outcomes are typically superior to locally denoised results. In contrast, Noise2Void and its variants do not utilize self-similarities in an image as the NLM-based methods do. Here we propose Noise2Sim, an NLM-inspired self-learning method for image denoising. Specifically, Noise2Sim leverages the self-similarity of image pixels to train the denoising network, requiring single noisy images only. Our theoretical analysis shows that Noise2Sim tends to be equivalent to Noise2Noise under mild conditions. To efficiently manage the computational burden for globally searching similar pixels, we design a two-step procedure to provide data for Noise2Sim training. Extensive experiments demonstrate the superiority of Noise2Sim on common benchmark datasets.
In this study, we propose a tailored DL framework for patient-specific performance that leverages the behavior of a model intentionally overfitted to a patient-specific training dataset augmented from the prior information available in an ART workflo
w - an approach we term Intentional Deep Overfit Learning (IDOL). Implementing the IDOL framework in any task in radiotherapy consists of two training stages: 1) training a generalized model with a diverse training dataset of N patients, just as in the conventional DL approach, and 2) intentionally overfitting this general model to a small training dataset-specific the patient of interest (N+1) generated through perturbations and augmentations of the available task- and patient-specific prior information to establish a personalized IDOL model. The IDOL framework itself is task-agnostic and is thus widely applicable to many components of the ART workflow, three of which we use as a proof of concept here: the auto-contouring task on re-planning CTs for traditional ART, the MRI super-resolution (SR) task for MRI-guided ART, and the synthetic CT (sCT) reconstruction task for MRI-only ART. In the re-planning CT auto-contouring task, the accuracy measured by the Dice similarity coefficient improves from 0.847 with the general model to 0.935 by adopting the IDOL model. In the case of MRI SR, the mean absolute error (MAE) is improved by 40% using the IDOL framework over the conventional model. Finally, in the sCT reconstruction task, the MAE is reduced from 68 to 22 HU by utilizing the IDOL framework.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
