Search Results for author:
Found 50 papers, 18 papers with code
UMedNeRF: Uncertainty-aware Single View Volumetric Rendering for Medical Neural Radiance Fields
In the field of clinical medicine, computed tomography (CT) is an effective medical imaging modality for the diagnosis of various pathologies.
Diffusion-based Radiotherapy Dose Prediction Guided by Inter-slice Aware Structure Encoding
In the forward process, DiffDose transforms dose distribution maps into pure Gaussian noise by gradually adding small noise and a noise predictor is simultaneously trained to estimate the noise added at each timestep.
X-Transfer: A Transfer Learning-Based Framework for Robust GAN-Generated Fake Image Detection
This model enhances transfer learning by utilizing two sibling neural networks that employ interleaved parallel gradient transmission.
Improving Cross-dataset Deepfake Detection with Deep Information Decomposition
Deepfake technology poses a significant threat to security and social trust.
Controlling Neural Style Transfer with Deep Reinforcement Learning
Controlling the degree of stylization in the Neural Style Transfer (NST) is a little tricky since it usually needs hand-engineering on hyper-parameters.
Weakly Supervised Semantic Segmentation by Knowledge Graph Inference
Extensive experimentation on both the multi-label classification and segmentation network stages underscores the effectiveness of the proposed graph reasoning approach for advancing WSSS.
Deep Reinforcement Learning for Image-to-Image Translation
The key feature in the RL-I2IT framework is to decompose a monolithic learning process into small steps with a lightweight model to progressively transform a source image successively to a target image.
Rethinking Superpixel Segmentation from Biologically Inspired Mechanisms
Recently, advancements in deep learning-based superpixel segmentation methods have brought about improvements in both the efficiency and the performance of segmentation.
Edge-aware Hard Clustering Graph Pooling for Brain Imaging
In this paper, we propose a novel edge-aware hard clustering graph pool (EHCPool), which is tailored to dominant edge features and redefines the clustering process.
TriDo-Former: A Triple-Domain Transformer for Direct PET Reconstruction from Low-Dose Sinograms
Specifically, the TriDo-Former consists of two cascaded networks, i. e., a sinogram enhancement transformer (SE-Former) for denoising the input LPET sinograms and a spatial-spectral reconstruction transformer (SSR-Former) for reconstructing SPET images from the denoised sinograms.
DiffDP: Radiotherapy Dose Prediction via a Diffusion Model
To alleviate this limitation, we innovatively introduce a diffusion-based dose prediction (DiffDP) model for predicting the radiotherapy dose distribution of cancer patients.
Dimension Independent Mixup for Hard Negative Sample in Collaborative Filtering
To address this limitation, we propose Dimension Independent Mixup for Hard Negative Sampling (DINS), which is the first Area-wise sampling method for training CF-based models.
Two Heads are Better than One: Towards Better Adversarial Robustness by Combining Transduction and Rejection
Nevertheless, under recent strong adversarial attacks (GMSA, which has been shown to be much more effective than AutoAttack against transduction), Goldwasser et al.'s work was shown to have low performance in a practical deep-learning setting.
Stratified Adversarial Robustness with Rejection
We theoretically analyze the stratified rejection setting and propose a novel defense method -- Adversarial Training with Consistent Prediction-based Rejection (CPR) -- for building a robust selective classifier.
Harnessing the Power of Text-image Contrastive Models for Automatic Detection of Online Misinformation
As growing usage of social media websites in the recent decades, the amount of news articles spreading online rapidly, resulting in an unprecedented scale of potentially fraudulent information.
The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
foundation models) has recently become a prevalent learning paradigm, where one first pre-trains a representation using large-scale unlabeled data, and then learns simple predictors on top of the representation using small labeled data from the downstream tasks.
Attacking Important Pixels for Anchor-free Detectors
Existing adversarial attacks on object detection focus on attacking anchor-based detectors, which may not work well for anchor-free detectors.
RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control
Reinforcement learning is applied to solve actual complex tasks from high-dimensional, sensory inputs.
Stochastic Planner-Actor-Critic for Unsupervised Deformable Image Registration
We evaluate our method on several 2D and 3D medical image datasets, some of which contain large deformations.
Stochastic Actor-Executor-Critic for Image-to-Image Translation
Training a model-free deep reinforcement learning model to solve image-to-image translation is difficult since it involves high-dimensional continuous state and action spaces.
Revisiting Adversarial Robustness of Classifiers With a Reject Option
Motivated by this metric, we propose novel loss functions and a robust training method -- \textit{stratified adversarial training with rejection} (SATR) -- for a classifier with reject option, where the goal is to accept and correctly-classify small input perturbations, while allowing the rejection of larger input perturbations that cannot be correctly classified.
Towards Evaluating the Robustness of Neural Networks Learned by Transduction
There has been emerging interest in using transductive learning for adversarial robustness (Goldwasser et al., NeurIPS 2020; Wu et al., ICML 2020; Wang et al., ArXiv 2021).
Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles
This observation leads to two challenging tasks: (1) unsupervised accuracy estimation, which aims to estimate the accuracy of a pre-trained classifier on a set of unlabeled test inputs; (2) error detection, which aims to identify mis-classified test inputs.
Towards Adversarial Robustness via Transductive Learning
Compared to traditional "test-time" defenses, these defense mechanisms "dynamically retrain" the model based on test time input via transductive learning; and theoretically, attacking these defenses boils down to bilevel optimization, which seems to raise the difficulty for adaptive attacks.
Imperceptible Adversarial Examples for Fake Image Detection
Fooling people with highly realistic fake images generated with Deepfake or GANs brings a great social disturbance to our society.
Transferable Adversarial Examples for Anchor Free Object Detection
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbation can completely change prediction result.
Deep Learning based Multi-modal Computing with Feature Disentanglement for MRI Image Synthesis
To take full advantage of the complementary information provided by different modalities, multi-modal MRI sequences are utilized as input.
Racetrack microresonator based electro-optic phase shifters on a 3C-silicon-carbide-on-insulator platform
We report the first demonstration of integrated electro-optic (EO) phase shifters based on racetrack microresonators on a 3C-silicon-carbide-on-insulator (SiCOI) platform working at near-infrared (NIR) wavelengths.
Optics Applied Physics
Multilayer Haldane model
We propose the model of layered materials, in which each layer is described by the conventional Haldane model, while the inter - layer hopping parameter corresponds to the ABC stacking.
Mesoscale and Nanoscale Physics
Test-Time Adaptation and Adversarial Robustness
On the positive side, we show that, if one is allowed to access the training data, then Domain Adversarial Neural Networks (${\sf DANN}$), an algorithm designed for unsupervised domain adaptation, can provide nontrivial robustness in the test-time maximin threat model against strong transfer attacks and adaptive fixed point attacks.
Fast Local Attack: Generating Local Adversarial Examples for Object Detectors
The deep neural network is vulnerable to adversarial examples.
ASMFS: Adaptive-Similarity-based Multi-modality Feature Selection for Classification of Alzheimer's Disease
With the increasing amounts of high-dimensional heterogeneous data to be processed, multi-modality feature selection has become an important research direction in medical image analysis.
Informative Outlier Matters: Robustifying Out-of-distribution Detection Using Outlier Mining
We show that, by mining informative auxiliary OOD data, one can significantly improve OOD detection performance, and somewhat surprisingly, generalize to unseen adversarial attacks.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
ATOM: Robustifying Out-of-distribution Detection Using Outlier Mining
We show that, by mining informative auxiliary OOD data, one can significantly improve OOD detection performance, and somewhat surprisingly, generalize to unseen adversarial attacks.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
DSU-net: Dense SegU-net for automatic head-and-neck tumor segmentation in MR images
In this paper, we propose a Dense SegU-net (DSU-net) framework for automatic NPC segmentation in MRI.
Representation Bayesian Risk Decompositions and Multi-Source Domain Adaptation
Recent studies provide hints and failure examples for domain invariant representation learning, a common approach for this problem, but the explanations provided are somewhat different and do not provide a unified picture.
Robust Out-of-distribution Detection for Neural Networks
Formally, we extensively study the problem of Robust Out-of-Distribution Detection on common OOD detection approaches, and show that state-of-the-art OOD detectors can be easily fooled by adding small perturbations to the in-distribution and OOD inputs.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Category-wise Attack: Transferable Adversarial Examples for Anchor Free Object Detection
Deep neural networks have been demonstrated to be vulnerable to adversarial attacks: subtle perturbations can completely change the classification results.
Robust Multimodal Image Registration Using Deep Recurrent Reinforcement Learning
To this end, these two components are tackled in an end-to-end manner via reinforcement learning in this work.
Discovery of Bias and Strategic Behavior in Crowdsourced Performance Assessment
With the industry trend of shifting from a traditional hierarchical approach to flatter management structure, crowdsourced performance assessment gained mainstream popularity.
Rearchitecting Classification Frameworks For Increased Robustness
and how to design a classification paradigm that leverages these invariances to improve the robustness accuracy trade-off?
Robust Attribution Regularization
An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions.
Concise Explanations of Neural Networks using Adversarial Training
Our first contribution is a theoretical exploration of how these two properties (when using attributions based on Integrated Gradients, or IG) are related to adversarial training, for a class of 1-layer networks (which includes logistic regression models for binary and multi-class classification); for these networks we show that (a) adversarial training using an $\ell_\infty$-bounded adversary produces models with sparse attribution vectors, and (b) natural model-training while encouraging stable explanations (via an extra term in the loss function), is equivalent to adversarial training.
Towards Understanding Limitations of Pixel Discretization Against Adversarial Attacks
We analyze our results in a theoretical framework and offer strong evidence that pixel discretization is unlikely to work on all but the simplest of the datasets.
The Manifold Assumption and Defenses Against Adversarial Perturbations
Interestingly, we find that a recent objective by Madry et al. encourages training a model that satisfies well our formal version of the goodness property, but has a weak control of points that are wrong but with low confidence.
Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training
In this paper we study leveraging confidence information induced by adversarial training to reinforce adversarial robustness of a given adversarially trained model.
Tuple-oriented Compression for Large-scale Mini-batch Stochastic Gradient Descent
We fill this crucial research gap by proposing a new lossless compression scheme we call tuple-oriented compression (TOC) that is inspired by an unlikely source, the string/text compression scheme Lempel-Ziv-Welch, but tailored to MGD in a way that preserves tuple boundaries within mini-batches.
Bolt-on Differential Privacy for Scalable Stochastic Gradient Descent-based Analytics
This paper takes a first step to remedy this disconnect and proposes a private SGD algorithm to address \emph{both} issues in an integrated manner.
Revisiting Differentially Private Regression: Lessons From Learning Theory and their Consequences
Perhaps more importantly, our theory reveals that the most basic mechanism in differential privacy, output perturbation, can be used to obtain a better tradeoff for all convex-Lipschitz-bounded learning tasks.
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
In this work, we introduce a defensive mechanism called defensive distillation to reduce the effectiveness of adversarial samples on DNNs.
