Deep learning models for semantic segmentation rely on expensive, large-scale, manually annotated datasets.
Ranked #15 on Semantic Segmentation on NYU Depth v2
We propose a hierarchical meta-learning-inspired model for music source separation (Meta-TasNet) in which a generator model is used to predict the weights of individual extractor models.
Ranked #17 on Music Source Separation on MUSDB18
Though Deep Neural Networks (DNN) show excellent performance across various computer vision tasks, several works show their vulnerability to adversarial samples, i. e., image samples with imperceptible noise engineered to manipulate the network's prediction.
In this work, we propose a data-efficient method which utilizes the geometric regularity of intraclass objects for pose estimation.
Such image comparison based approach also alleviates the problem of data scarcity and hence enhances scalability of the proposed approach for novel object categories with minimal annotation.
Further, via exploiting simple priors related to the data distribution, our objective remarkably boosts the fooling ability of the crafted perturbations.