Class-agnostic object detection
Object detection models perform well at localizing and classifying objects that they are
shown during training. However, due to the difficulty and cost associated with creating and …
shown during training. However, due to the difficulty and cost associated with creating and …
Invariant representations through adversarial forgetting
We propose a novel approach to achieving invariance for deep neural networks in the form
of inducing amnesia to unwanted factors of data through a new adversarial forgetting …
of inducing amnesia to unwanted factors of data through a new adversarial forgetting …
A study of bias mitigation strategies for speaker recognition
Speaker recognition is increasingly used in several everyday applications including smart
speakers, customer care centers and other speech-driven analytics. It is crucial to accurately …
speakers, customer care centers and other speech-driven analytics. It is crucial to accurately …
Learning invariant representations using inverse contrastive loss
Learning invariant representations is a critical first step in a number of machine learning
tasks. A common approach is given by the so-called information bottleneck principle in …
tasks. A common approach is given by the so-called information bottleneck principle in …
Information bottleneck disentanglement based sparse representation for fair classification
Unlike current state-of-the-art methods based on data augmentation and adversarial
frameworks to solve the fair classification problem, this paper proposes the Information …
frameworks to solve the fair classification problem, this paper proposes the Information …
Discovery and separation of features for invariant representation learning
Supervised machine learning models often associate irrelevant nuisance factors with the
prediction target, which hurts generalization. We propose a framework for training robust …
prediction target, which hurts generalization. We propose a framework for training robust …
Learning invariant representation of tasks for robust surgical state estimation
Surgical state estimators in robot-assisted surgery (RAS)-especially those trained via
learning techniques-rely heavily on datasets that capture surgeon actions in laboratory or …
learning techniques-rely heavily on datasets that capture surgeon actions in laboratory or …
Pooling Image Datasets With Multiple Covariate Shift and Imbalance
Small sample sizes are common in many disciplines, which necessitates pooling roughly
similar datasets across multiple institutions to study weak but relevant associations between …
similar datasets across multiple institutions to study weak but relevant associations between …
Niesr: Nuisance invariant end-to-end speech recognition
Deep neural network models for speech recognition have achieved great success recently,
but they can learn incorrect associations between the target and nuisance factors of speech …
but they can learn incorrect associations between the target and nuisance factors of speech …
To train or not to train adversarially: A study of bias mitigation strategies for speaker recognition
Speaker recognition is increasingly used in several everyday applications including smart
speakers, customer care centers and other speech-driven analytics. It is crucial to accurately …
speakers, customer care centers and other speech-driven analytics. It is crucial to accurately …