Search Results for author:
Found 9 papers, 4 papers with code
Fusion is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection
We argue that the weakest link of fusion models depends on their most vulnerable modality, and propose an attack framework that targets advanced camera-LiDAR fusion-based 3D object detection models through camera-only adversarial attacks.
Leveraging Angular Distributions for Improved Knowledge Distillation
AMD loss uses the angular distance between positive and negative features by projecting them onto a hypersphere, motivated by the near angular distributions seen in many feature extractors.
Understanding the Role of Mixup in Knowledge Distillation: An Empirical Study
Mixup is a popular data augmentation technique based on creating new samples by linear interpolation between two given data samples, to improve both the generalization and robustness of the trained model.
Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
Experimental results show that our method can generate stealthy, effective, and robust adversarial patches for different target objects and models and achieves more than 6 meters mean depth estimation error and 93% attack success rate (ASR) in object detection with a patch of 1/9 of the vehicle's rear area.
Interpretable COVID-19 Chest X-Ray Classification via Orthogonality Constraint
In addition to these findings, our work also presents a new application of the OS regularizer in healthcare, increasing the post-hoc interpretability and performance of deep learning models for COVID-19 classification to facilitate adoption of these methods in clinical settings.
Role of Orthogonality Constraints in Improving Properties of Deep Networks for Image Classification
Standard deep learning models that employ the categorical cross-entropy loss are known to perform well at image classification tasks.
Automatic Cross-Replica Sharding of Weight Update in Data-Parallel Training
In data-parallel synchronous training of deep neural networks, different devices (replicas) run the same program with different partitions of the training batch, but weight update computation is repeated on all replicas, because the weights do not have a batch dimension to partition.
AMC-Loss: Angular Margin Contrastive Loss for Improved Explainability in Image Classification
We find that although the proposed geometrically constrained loss-function improves quantitative results modestly, it has a qualitatively surprisingly beneficial effect on increasing the interpretability of deep-net decisions as seen by the visual explanations generated by techniques such as the Grad-CAM.
PI-Net: A Deep Learning Approach to Extract Topological Persistence Images
To the best of our knowledge, we are the first to propose the use of deep learning for computing topological features directly from data.
