Deep neural networks are discovered to be non-robust when attacked by imperceptible adversarial examples, which is dangerous for it applied into medical diagnostic system that requires high reliability. However, the defense methods that have good effect in natural images may not be suitable for medical diagnostic tasks. The preprocessing methods (e.g., random resizing, compression) may lead to the loss of the small lesions feature in the medical image. Retraining the network on the augmented data set is also not practical for medical models that have already been deployed online. Accordingly, it is necessary to design an easy-to-deploy and effective defense framework for medical diagnostic tasks. In this paper, we propose a Robust and Retrain-Less Diagnostic Framework for Medical pretrained models against adversarial attack (i.e., MedRDF). It acts on the inference time of the pertained medical model. Specifically, for each test image, MedRDF firstly creates a large number of noisy copies of it, and obtains the output labels of these copies from the pretrained medical diagnostic model. Then, based on the labels of these copies, MedRDF outputs the final robust diagnostic result by majority voting. In addition to the diagnostic result, MedRDF produces the Robust Metric (RM) as the confidence of the result. Therefore, it is convenient and reliable to utilize MedRDF to convert pre-trained non-robust diagnostic models into robust ones. The experimental results on COVID-19 and DermaMNIST datasets verify the effectiveness of our MedRDF in improving the robustness of medical diagnostic models.
Google（谷歌）；Carnegie Mellon University（卡内基梅隆大学）；Bosch Center for AI（博世人工智能中心）
In this paper we show how to achieve state-of-the-art certified adversarial robustness to 2-norm bounded perturbations by relying exclusively on off-the-shelf pretrained models. To do so, we instantiate the denoised smoothing approach of Salman et al. 2020 by combining a pretrained denoising diffusion probabilistic model and a standard high-accuracy classifier. This allows us to certify 71% accuracy on ImageNet under adversarial perturbations constrained to be within an 2-norm of 0.5, an improvement of 14 percentage points over the prior certified SoTA using any approach, or an improvement of …
Activation-Space Uncertainty Quantification for Pretrained Networks
Department of Engineering, University of Cambridge, Cambridge, UK（剑桥大学工程系）；Mathematical Institute（数学研究所）；Oxford-Man Institute, University of Oxford, Oxford, UK（牛津大学奥克斯曼研究所）
Image classification has significantly improved using deep learning. This is mainly due to convolutional neural networks (CNNs) that are capable of learning rich feature extractors from large datasets. However, most deep learning classification methods are trained on clean images and are not robust when handling noisy ones, even if a restoration preprocessing step is applied. While novel methods address this problem, they rely on modified feature extractors and thus necessitate retraining. We instead propose a method that can be applied on a $pretrained$ classifier. Our method exploits a fidel…
Institute of Science and Technology, Austria（奥地利科学技术研究所）；Carnegie Mellon University（卡内基梅隆大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Chan Zuckerberg Initiative（陈·扎克伯格倡议）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ELLIS Institute Tübingen（图宾根ELLIS研究所）
Collaborative inference enables resource-constrained edge devices to make inferences by uploading inputs (e.g., images) to a server (i.e., cloud) where the heavy deep learning models run. While this setup works cost-effectively for successful inferences, it severely underperforms when the model faces input samples on which the model was not trained (known as Out-of-Distribution (OOD) samples). If the edge devices could, at least, detect that an input sample is an OOD, that could potentially save communication and computation resources by not uploading those inputs to the server for inference w…
Stanford University（斯坦福大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Current semantic segmentation models cannot easily generalize to new object classes unseen during train time: they require additional annotated images and retraining. We propose a novel segmentation model that injects visual priors into semantic segmentation architectures, allowing them to segment out new target labels without retraining. As visual priors, we use the activations of pretrained image classifiers, which provide noisy indications of the spatial location of both the target object and distractor objects in the scene. We leverage language semantics to obtain these activations for a t…
Inria（法国国家科学研究中心）；PreMeDICaL, Inserm, Montpellier, France（PreMeDICaL、法国国家医学研究院、蒙彼利埃，法国）；School of Computer and Communication Science (EPFL)（信息与通信科学学院（EPFL））；School of Life Sciences (EPFL)（生命科学学院（EPFL））；Lausanne, Switzerland（瑞士洛桑）
Uncertainty Estimation for Pretrained Medical Image Registration Models via Transformation Equivariance
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；The Hawkes Institute, University College London（霍克斯研究所，伦敦大学学院）；AI Laboratory, Massachusetts Institute of Technology（人工智能实验室，麻省理工学院）
Breaking the Likelihood-Quality Trade-off in Diffusion Models by Merging Pretrained Experts
Saarland University（萨尔兰大学）；Helmholtz AI（亥姆霍兹人工智能研究所）；Technical University of Munich（慕尼黑技术大学）；CISPA Helmholtz Center for Information Security（亥姆霍兹信息安全部分研究所）；MPI for Intelligent Systems, Tübingen（图宾根智能系统研究所）
INESC-ID；Instituto Superior Técnico（高等技术学院）；University of Lisbon（里斯本大学）；University of Copenhagen（哥本哈根大学）
Inspired by retrieval-augmented language generation and pretrained Vision and Language (V&L) encoders, we present a new approach to image captioning that generates sentences given the input image and a set of captions retrieved from a datastore, as opposed to the image alone. The encoder in our model jointly processes the image and retrieved captions using a pretrained V&L BERT, while the decoder attends to the multimodal encoder representations, benefiting from the extra textual evidence from the retrieved captions. Experimental results on the COCO dataset show that image captioning can be ef…
