( Image credit: Albumentations )
Deep Neural Networks (DNNs) in Computer Vision (CV) are well-known to be vulnerable to Adversarial Examples (AEs), namely imperceptible perturbations added maliciously to cause wrong classification results.
The accuracy, precision, sensitivity, F1-score, specificity in the detection of tuberculosis using X-ray images were 97. 07 %, 97. 34 %, 97. 07 %, 97. 14 % and 97. 36 % respectively.
In the present paper, we propose a decoder-free extension of Dreamer, a leading model-based reinforcement learning (MBRL) method from pixels.
As a result, this model performs quite well in both validation and explanation.
We train the deep neural network only in the simulated environment; and the trained model could be directly used for real-world visual servoing tasks.
Our data analysis on facial attribute recognition demonstrates (1) the attribution of model bias from imbalanced training data distribution and (2) the potential of adversarial examples in balancing data distribution.
In this paper, we propose part-aware data augmentation (PA-AUG) that can better utilize rich information of 3D label to enhance the performance of 3D object detectors.
DeepInfoMax (DIM) is a self-supervised method which leverages the internal structure of deep networks to construct such views, forming prediction tasks between local features which depend on small patches in an image and global features which depend on the whole image.
We argue that for pair-wise matchers that rely on metric learning, e. g., Siamese networks for person ReID, the unsupervised domain adaptation (UDA) objective should consist in aligning pair-wise dissimilarity between domains, rather than aligning feature representations.