11 citations · 37 across the 21 of their papers we have counts for
23 papers
AlignGuard: Scalable Safety Alignment for Text-to-Image Generation
Runtao Liu, I Chieh Chen, Jindong Gu +6
Text-to-image (T2I) models are widespread, but their limited safety guardrails expose end users to harmful content and potentially allow for model misuse. Current safety measures a…
Learnable Sparsity for Vision Generative Models
Yang Zhang, Er Jin, Wenzhong Liang +5
Diffusion models have achieved impressive advancements in various vision tasks. However, these gains often rely on increasing model size, which escalates computational complexity a…
Learning Visual Prompts for Guiding the Attention of Vision Transformers
Razieh Rezaei, Masoud Jalili Sabet, Jindong Gu +3
Visual prompting infuses visual information into the input image to adapt models toward specific predictions and tasks. Recently, manually crafted markers such as red circles are s…
Latent Guard: a Safety Framework for Text-to-image Generation
Runtao Liu, Ashkan Khakzar, Jindong Gu +3
With the ability to generate high-quality images, text-to-image (T2I) models can be exploited for creating inappropriate content. To prevent misuse, existing safety measures are ei…
On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions
Razieh Rezaei, Alireza Dizaji, Ashkan Khakzar +3
Neural networks are increasingly finding their way into the realm of graphs and modeling relationships between features. Concurrently graph neural network explanation approaches ar…
A Survey on Transferability of Adversarial Examples across Deep Neural Networks
Jindong Gu, Xiaojun Jia, Pau de Jorge +9
The emergence of Deep Neural Networks (DNNs) has revolutionized various domains by enabling the resolution of complex tasks spanning image recognition, natural language processing,…
AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments
Yang Zhang, Yawei Li, Hannah Brown +5
Feature attribution explains neural network outputs by identifying relevant input features. The attribution has to be faithful, meaning that the attributed features must mirror the…
A Dual-Perspective Approach to Evaluating Feature Attribution Methods
Yawei Li, Yang Zhang, Kenji Kawaguchi +3
Feature attribution methods attempt to explain neural network predictions by identifying relevant features. However, establishing a cohesive framework for assessing feature attribu…
Pixel-Level Explanation of Multiple Instance Learning Models in Biomedical Single Cell Images
Ario Sadafi, Oleksandra Adonkina, Ashkan Khakzar +5
Explainability is a key requirement for computer-aided diagnosis systems in clinical decision-making. Multiple instance learning with attention pooling provides instance-level expl…
CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN
Matan Atad, Vitalii Dmytrenko, Yitong Li +6
Deep learning models used in medical image analysis are prone to raising reliability concerns due to their black-box nature. To shed light on these black-box models, previous works…
Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models
Ashkan Khakzar, Yawei Li, Yang Zhang +5
One challenging property lurking in medical datasets is the imbalanced data distribution, where the frequency of the samples between the different classes is not balanced. Training…
Interpretable Vertebral Fracture Diagnosis
Paul Engstler, Matthias Keicher, David Schinz +11
Do black-box neural network models learn clinically relevant features for fracture diagnosis? The answer not only establishes reliability quenches scientific curiosity but also lea…
Do Explanations Explain? Model Knows Best
Ashkan Khakzar, Pedram Khorsandi, Rozhin Nobahari +1
It is a mystery which input features contribute to a neural network's output. Various explanation (feature attribution) methods are proposed in the literature to shed light on the…
FlexR: Few-shot Classification with Language Embeddings for Structured Reporting of Chest X-rays
Matthias Keicher, Kamilia Zaripova, Tobias Czempiel +3
The automation of chest X-ray reporting has garnered significant interest due to the time-consuming nature of the task. However, the clinical accuracy of free-text reports has prov…
Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
Yang Zhang, Ashkan Khakzar, Yawei Li +3
One principal approach for illuminating a black-box neural network is feature attribution, i.e. identifying the importance of input features for the network's prediction. The predi…
Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Models
Ashkan Khakzar, Sabrina Musatian, Jonas Buchberger +5
Convolutional neural networks are showing promise in the automatic diagnosis of thoracic pathologies on chest x-rays. Their black-box nature has sparked many recent works to explai…
Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features
Ashkan Khakzar, Yang Zhang, Wejdene Mansour +5
Neural networks have demonstrated remarkable performance in classification and regression tasks on chest X-rays. In order to establish trust in the clinical routine, the networks'…
Neural Response Interpretation through the Lens of Critical Pathways
Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja +3
Is critical input information encoded in specific sparse pathways within the neural network? In this work, we discuss the problem of identifying these critical pathways and subsequ…
Longitudinal Quantitative Assessment of COVID-19 Infection Progression from Chest CTs
Seong Tae Kim, Leili Goli, Magdalini Paschali +7
Chest computed tomography (CT) has played an essential diagnostic role in assessing patients with COVID-19 by showing disease-specific image features such as ground-glass opacity a…
Rethinking Positive Aggregation and Propagation of Gradients in Gradient-based Saliency Methods
Ashkan Khakzar, Soroosh Baselizadeh, Nassir Navab
Saliency methods interpret the prediction of a neural network by showing the importance of input elements for that prediction. A popular family of saliency methods utilize gradient…
Spatio-temporal Learning from Longitudinal Data for Multiple Sclerosis Lesion Segmentation
Stefan Denner, Ashkan Khakzar, Moiz Sajid +4
Segmentation of Multiple Sclerosis (MS) lesions in longitudinal brain MR scans is performed for monitoring the progression of MS lesions. We hypothesize that the spatio-temporal cu…
Improving Feature Attribution through Input-specific Network Pruning
Ashkan Khakzar, Soroosh Baselizadeh, Saurabh Khanduja +3
Attributing the output of a neural network to the contribution of given input elements is a way of shedding light on the black-box nature of neural networks. Due to the complexity…
Learning Interpretable Features via Adversarially Robust Optimization
Ashkan Khakzar, Shadi Albarqouni, Nassir Navab
Neural networks are proven to be remarkably successful for classification and diagnosis in medical applications. However, the ambiguity in the decision-making process and the inter…