关注
Chaithanya Kumar Mummadi
Chaithanya Kumar Mummadi
Machine Learning Research Scientist, Bosch Center for Artificial Intelligence, Robert Bosch LLC, USA
在 bosch.com 的电子邮件经过验证
标题
引用次数
引用次数
年份
Self: Learning to filter noisy labels with self-ensembling
DT Nguyen, CK Mummadi, TPN Ngo, THP Nguyen, L Beggel, T Brox
arXiv preprint arXiv:1910.01842, 2019
3392019
Universal adversarial perturbations against semantic image segmentation
J Hendrik Metzen, M Chaithanya Kumar, T Brox, V Fischer
Proceedings of the IEEE international conference on computer vision, 2755-2764, 2017
3392017
Deepusps: Deep robust unsupervised saliency prediction via self-supervision
T Nguyen, M Dax, CK Mummadi, N Ngo, THP Nguyen, Z Lou, T Brox
Advances in Neural Information Processing Systems 32, 2019
1482019
Adversarial examples for semantic image segmentation
V Fischer, MC Kumar, JH Metzen, T Brox
arXiv preprint arXiv:1703.01101, 2017
1402017
Real-time and embedded detection of hand gestures with an IMU-based glove
CK Mummadi, F Philips Peter Leo, K Deep Verma, S Kasireddy, ...
Informatics 5 (2), 28, 2018
862018
Defending against universal perturbations with shared adversarial training
CK Mummadi, T Brox, JH Metzen
Proceedings of the IEEE/CVF international conference on computer vision …, 2019
642019
Test-time adaptation to distribution shift by confidence maximization and input transformation
CK Mummadi, R Hutmacher, K Rambach, E Levinkov, T Brox, JH Metzen
arXiv preprint arXiv:2106.14999, 2021
562021
Does enhanced shape bias improve neural network robustness to common corruptions?
CK Mummadi, R Subramaniam, R Hutmacher, J Vitay, V Fischer, ...
arXiv preprint arXiv:2104.09789, 2021
362021
Give me your attention: Dot-product attention considered harmful for adversarial patch robustness
G Lovisotto, N Finnie, M Munoz, CK Mummadi, JH Metzen
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022
322022
Real-time embedded recognition of sign language alphabet fingerspelling in an IMU-based glove
CK Mummadi, FPP Leo, KD Verma, S Kasireddy, PM Scholl, ...
Proceedings of the 4th international Workshop on Sensor-based Activity …, 2017
292017
Diagvib-6: A diagnostic benchmark suite for vision models in the presence of shortcut and generalization opportunities
E Eulig, P Saranrittichai, CK Mummadi, K Rambach, W Beluch, X Shi, ...
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
92021
Group Pruning Using a Bounded- Norm for Group Gating and Regularization
CK Mummadi, T Genewein, D Zhang, T Brox, V Fischer
German Conference on Pattern Recognition, 139-155, 2019
72019
Overcoming shortcut learning in a target domain by generalizing basic visual factors from a source domain
P Saranrittichai, CK Mummadi, C Blaiotta, M Munoz, V Fischer
European Conference on Computer Vision, 294-309, 2022
62022
More context, less distraction: Visual classification by inferring and conditioning on contextual attributes
B An, S Zhu, MA Panaitescu-Liess, CK Mummadi, F Huang
arXiv preprint arXiv:2308.01313, 2023
52023
Text-driven prompt generation for vision-language models in federated learning
C Qiu, X Li, CK Mummadi, MR Ganesh, Z Li, L Peng, WY Lin
arXiv preprint arXiv:2310.06123, 2023
42023
Multi-attribute open set recognition
P Saranrittichai, CK Mummadi, C Blaiotta, M Munoz, V Fischer
DAGM German Conference on Pattern Recognition, 101-115, 2022
42022
Federated text-driven prompt generation for vision-language models
C Qiu, X Li, CK Mummadi, MR Ganesh, Z Li, L Peng, WY Lin
The Twelfth International Conference on Learning Representations, 2024
22024
Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches
A Saha, S Yu, A Norouzzadeh, WY Lin, CK Mummadi
arXiv preprint arXiv:2306.12610, 2023
22023
AutoCLIP: Auto-tuning Zero-Shot Classifiers for Vision-Language Models
JH Metzen, P Saranrittichai, CK Mummadi
arXiv preprint arXiv:2309.16414, 2023
12023
More context, less distraction: Improving zero-shot inference of clip by inferring and describing spurious features
B An, S Zhu, MA Panaitescu-Liess, CK Mummadi, F Huang
Workshop on Efficient Systems for Foundation Models@ ICML2023, 2023
12023
系统目前无法执行此操作,请稍后再试。
文章 1–20