4 papers · 1 filter
PartImageNet++ Dataset: Enhancing Visual Models with High-Quality Part Annotations
Xiao Li, Zilong Liu, Yining Liu +4
To address the scarcity of high-quality part annotations in existing datasets, we introduce PartImageNet++ (PIN++), a dataset that provides detailed part annotations for all catego…
From Healthy Scans to Annotated Tumors: A Tumor Fabrication Framework for 3D Brain MRI Synthesis
Nayu Dong, Townim Chowdhury, Hieu Phan +3
The scarcity of annotated Magnetic Resonance Imaging (MRI) tumor data presents a major obstacle to accurate and automated tumor segmentation. While existing data synthesis methods…
Looking in the mirror: A faithful counterfactual explanation method for interpreting deep image classification models
Townim Faisal Chowdhury, Vu Minh Hieu Phan, Kewen Liao +5
Counterfactual explanations (CFE) for deep image classifiers aim to reveal how minimal input changes lead to different model decisions, providing critical insights for model interp…
PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition
Xiao Li, Yining Liu, Na Dong +2
Deep learning-based object recognition systems can be easily fooled by various adversarial perturbations. One reason for the weak robustness may be that they do not have part-based…