User profiles for Chaithanya Kumar Mummadi
Chaithanya Kumar MummadiMachine Learning Research Scientist, Bosch Center for Artificial Intelligence, Robert Bosch�… Verified email at bosch.com Cited by 1395 |
Self: Learning to filter noisy labels with self-ensembling
Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained
with noisy labels for a long enough time. To overcome this problem, we present a simple and …
with noisy labels for a long enough time. To overcome this problem, we present a simple and …
Universal adversarial perturbations against semantic image segmentation
…, M Chaithanya Kumar…�- Proceedings of the�…, 2017 - openaccess.thecvf.com
While deep learning is remarkably successful on perceptual tasks, it was also shown to be
vulnerable to adversarial perturbations of the input. These perturbations denote noise added …
vulnerable to adversarial perturbations of the input. These perturbations denote noise added …
Defending against universal perturbations with shared adversarial training
CK Mummadi, T Brox…�- Proceedings of the IEEE�…, 2019 - openaccess.thecvf.com
Classifiers such as deep neural networks have been shown to be vulnerable against
adversarial perturbations on problems with high-dimensional input space. While adversarial …
adversarial perturbations on problems with high-dimensional input space. While adversarial …
Test-time adaptation to distribution shift by confidence maximization and input transformation
Deep neural networks often exhibit poor performance on data that is unlikely under the train-time
data distribution, for instance data affected by corruptions. Previous works demonstrate …
data distribution, for instance data affected by corruptions. Previous works demonstrate …
Does enhanced shape bias improve neural network robustness to common corruptions?
CK Mummadi, R Subramaniam, R Hutmacher…�- arXiv preprint arXiv�…, 2021 - arxiv.org
Convolutional neural networks (CNNs) learn to extract representations of complex features,
such as object shapes and textures to solve image recognition tasks. Recent work indicates …
such as object shapes and textures to solve image recognition tasks. Recent work indicates …
[HTML][HTML] Real-time and embedded detection of hand gestures with an IMU-based glove
CK Mummadi, F Philips Peter Leo, K Deep Verma…�- Informatics, 2018 - mdpi.com
This article focuses on the use of data gloves for human-computer interaction concepts,
where external sensors cannot always fully observe the user’s hand. A good concept hereby …
where external sensors cannot always fully observe the user’s hand. A good concept hereby …
Deepusps: Deep robust unsupervised saliency prediction via self-supervision
Deep neural network (DNN) based salient object detection in images based on high-quality
labels is expensive. Alternative unsupervised approaches rely on careful selection of …
labels is expensive. Alternative unsupervised approaches rely on careful selection of …
Adversarial examples for semantic image segmentation
Machine learning methods in general and Deep Neural Networks in particular have shown
to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been …
to be vulnerable to adversarial perturbations. So far this phenomenon has mainly been …
Give me your attention: Dot-product attention considered harmful for adversarial patch robustness
Neural architectures based on attention such as vision transformers are revolutionizing image
recognition. Their main benefit is that attention allows reasoning about all parts of a scene …
recognition. Their main benefit is that attention allows reasoning about all parts of a scene …
Real-time embedded recognition of sign language alphabet fingerspelling in an IMU-based glove
CK Mummadi, FPP Leo, KD Verma…�- Proceedings of the 4th�…, 2017 - dl.acm.org
Data gloves have numerous applications, including enabling novel human-computer
interaction and automated recognition of large sets of gestures, such as those used for sign …
interaction and automated recognition of large sets of gestures, such as those used for sign …