Search Results for author:
Found 3 papers, 2 papers with code
ObjectCompose: Evaluating Resilience of Vision-Based Models on Object-to-Background Compositional Changes
We produce various versions of standard vision datasets (ImageNet, COCO), incorporating either diverse and realistic backgrounds into the images or introducing color, texture, and adversarial changes in the background.
Adversarial Pixel Restoration as a Pretext Task for Transferable Perturbations
Our training approach is based on a min-max scheme which reduces overfitting via an adversarial objective and thus optimizes for a more generalizable surrogate model.
Object Detection in Aerial Images: What Improves the Accuracy?
In this work, we investigate the impact of Faster R-CNN for aerial object detection and explore numerous strategies to improve its performance for aerial images.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
