In this paper, we present TransAug (Translate as Augmentation), which provide the first exploration of utilizing translated sentence pairs as data augmentation for text, and introduce a two-stage paradigm to advances the state-of-the-art sentence embeddings.
Extra rich non-paired single-modal text data is used for boosting the generalization of text branch.
Given the increase in the use of personal data for training Deep Neural Networks (DNNs) in tasks such as medical imaging and diagnosis, differentially private training of DNNs is surging in importance and there is a large body of work focusing on providing better privacy-utility trade-off.
Interpretation of the underlying mechanisms of Deep Convolutional Neural Networks has become an important aspect of research in the field of deep learning due to their applications in high-risk environments.
Feature attributions are a popular tool for explaining the behavior of Deep Neural Networks (DNNs), but have recently been shown to be vulnerable to attacks that produce divergent explanations for nearby inputs.
Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions.
We introduce a new model-agnostic explanation technique which explains the prediction of any classifier called CLE.
In this paper, to do the estimation without facial landmarks, we combine the coarse and fine regression output together for a deep network.
Ranked #2 on Head Pose Estimation on BIWI (MAE (trained with BIWI data) metric)