Search Results for author:
Found 27 papers, 14 papers with code
SafetyDPO: Scalable Safety Alignment for Text-to-Image Generation
Using a custom DPO strategy and this dataset, we train safety experts, in the form of low-rank adaptation (LoRA) matrices, able to guide the generation process away from specific safety-related concepts.
Effortless Efficiency: Low-Cost Pruning of Diffusion Models
Diffusion models have achieved impressive advancements in various vision tasks.
Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models
Despite the importance of shape perception in human vision, early neural image classifiers relied less on shape information for object recognition than other (often spurious) features.
Sparse Autoencoders Reveal Universal Feature Spaces Across Large Language Models
We investigate feature universality in large language models (LLMs), a research field that aims to understand how different models similarly represent concepts in the latent spaces of their intermediate layers.
The Cognitive Revolution in Interpretability: From Explaining Behavior to Interpreting Representations and Algorithms
Artificial neural networks have long been understood as "black boxes": though we know their computation graphs and learned parameters, the knowledge encoded by these weights and functions they perform are not inherently interpretable.
Learning Visual Prompts for Guiding the Attention of Vision Transformers
The learned visual prompt, added to any input image would redirect the attention of the pre-trained vision transformer to its spatial location on the image.
Latent Guard: a Safety Framework for Text-to-image Generation
Hence, we propose Latent Guard, a framework designed to improve safety measures in text-to-image generation.
On Discprecncies between Perturbation Evaluations of Graph Neural Network Attributions
In this work, we assess attribution methods from a perspective not previously explored in the graph domain: retraining.
A Survey on Transferability of Adversarial Examples across Deep Neural Networks
This survey explores the landscape of the adversarial transferability of adversarial examples.
AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments
Feature attribution explains neural network outputs by identifying relevant input features.
A Dual-Perspective Approach to Evaluating Feature Attribution Methods
We apply these metrics to mainstream attribution methods, offering a novel lens through which to analyze and compare feature attribution methods.
Pixel-Level Explanation of Multiple Instance Learning Models in Biomedical Single Cell Images
Explainability is a key requirement for computer-aided diagnosis systems in clinical decision-making.
CheXplaining in Style: Counterfactual Explanations for Chest X-rays using StyleGAN
Deep learning models used in medical image analysis are prone to raising reliability concerns due to their black-box nature.
Analyzing the Effects of Handling Data Imbalance on Learned Features from Medical Images by Looking Into the Models
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.
Interpretable Vertebral Fracture Diagnosis
Do black-box neural network models learn clinically relevant features for fracture diagnosis?
FlexR: Few-shot Classification with Language Embeddings for Structured Reporting of Chest X-rays
The automation of chest X-ray reporting has garnered significant interest due to the time-consuming nature of the task.
Do Explanations Explain? Model Knows Best
It is a mystery which input features contribute to a neural network's output.
Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
We propose a method to identify features with predictive information in the input domain.
Towards Semantic Interpretation of Thoracic Disease and COVID-19 Diagnosis Models
We present our findings using publicly available chest pathologies (CheXpert, NIH ChestX-ray8) and COVID-19 datasets (BrixIA, and COVID-19 chest X-ray segmentation dataset).
Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features
Neural networks have demonstrated remarkable performance in classification and regression tasks on chest X-rays.
Neural Response Interpretation through the Lens of Critical Pathways
Is critical input information encoded in specific sparse pathways within the neural network?
Longitudinal Quantitative Assessment of COVID-19 Infection Progression from Chest CTs
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 and consolidation.
On Sparse Critical Paths of Neural Response
Is critical input information encoded in specific sparse paths within the network?
Rethinking Positive Aggregation and Propagation of Gradients in Gradient-based Saliency Methods
In this work, we empirically show that two approaches for handling the gradient information, namely positive aggregation, and positive propagation, break these methods.
Spatio-temporal Learning from Longitudinal Data for Multiple Sclerosis Lesion Segmentation
Our results show that spatio-temporal information in longitudinal data is a beneficial cue for improving segmentation.
Improving Feature Attribution through Input-specific Network Pruning
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.
Learning Interpretable Features via Adversarially Robust Optimization
In this work, we propose a method for improving the feature interpretability of neural network classifiers.
