no code implementations • 9 Oct 2023 • Chen Qiu, Xingyu Li, Chaithanya Kumar Mummadi, Madan Ravi Ganesh, Zhenzhen Li, Lu Peng, Wan-Yi Lin
Prompt learning for vision-language models, e. g., CoOp, has shown great success in adapting CLIP to different downstream tasks, making it a promising solution for federated learning due to computational reasons.
no code implementations • 28 Sep 2023 • Jan Hendrik Metzen, Piyapat Saranrittichai, Chaithanya Kumar Mummadi
We show that AutoCLIP outperforms baselines across a broad range of vision-language models, datasets, and prompt templates consistently and by up to 3 percent point accuracy.
no code implementations • 12 Sep 2023 • Piyapat Saranrittichai, Mauricio Munoz, Volker Fischer, Chaithanya Kumar Mummadi
We empirically show that our approach improves zero-shot classification results across architectures and datasets, favorably for small objects.
1 code implementation • 2 Aug 2023 • Bang An, Sicheng Zhu, Michael-Andrei Panaitescu-Liess, Chaithanya Kumar Mummadi, Furong Huang
Inspired by it, we observe that providing CLIP with contextual attributes improves zero-shot image classification and mitigates reliance on spurious features.
no code implementations • 22 Jun 2023 • Aniruddha Saha, Shuhua Yu, Arash Norouzzadeh, Wan-Yi Lin, Chaithanya Kumar Mummadi
The success of this strategy relies heavily on the model's invariance to image pixel masking.
1 code implementation • 14 Aug 2022 • Piyapat Saranrittichai, Chaithanya Kumar Mummadi, Claudia Blaiotta, Mauricio Munoz, Volker Fischer
While conventional OSR approaches can detect Out-of-Distribution (OOD) samples, they cannot provide explanations indicating which underlying visual attribute(s) (e. g., shape, color or background) cause a specific sample to be unknown.
1 code implementation • 20 Jul 2022 • Piyapat Saranrittichai, Chaithanya Kumar Mummadi, Claudia Blaiotta, Mauricio Munoz, Volker Fischer
Our approach extends the training set with an additional dataset (the source domain), which is specifically designed to facilitate learning independent representations of basic visual factors.
no code implementations • CVPR 2022 • Giulio Lovisotto, Nicole Finnie, Mauricio Munoz, Chaithanya Kumar Mummadi, Jan Hendrik Metzen
Neural architectures based on attention such as vision transformers are revolutionizing image recognition.
1 code implementation • ICCV 2021 • Elias Eulig, Piyapat Saranrittichai, Chaithanya Kumar Mummadi, Kilian Rambach, William Beluch, Xiahan Shi, Volker Fischer
We also argue that it is necessary for DNNs to exploit GO to overcome shortcut learning.
no code implementations • 28 Jun 2021 • Chaithanya Kumar Mummadi, Robin Hutmacher, Kilian Rambach, Evgeny Levinkov, Thomas Brox, Jan Hendrik Metzen
This paper focuses on the fully test-time adaptation setting, where only unlabeled data from the target distribution is required.
no code implementations • NeurIPS 2021 • Chaithanya Kumar Mummadi, Robin Hutmacher, Kilian Rambach, Evgeny Levinkov, Thomas Brox, Jan Hendrik Metzen
This paper focuses on the fully test-time adaptation setting, where only unlabeled data from the target distribution is required.
no code implementations • ICLR 2021 • Chaithanya Kumar Mummadi, Ranjitha Subramaniam, Robin Hutmacher, Julien Vitay, Volker Fischer, Jan Hendrik Metzen
We conclude that the data augmentation caused by style-variation accounts for the improved corruption robustness and increased shape bias is only a byproduct.
no code implementations • NeurIPS 2019 • Tam Nguyen, Maximilian Dax, Chaithanya Kumar Mummadi, Nhung Ngo, Thi Hoai Phuong Nguyen, Zhongyu Lou, Thomas Brox
Alternative unsupervised approaches rely on careful selection of multiple handcrafted saliency methods to generate noisy pseudo-ground-truth labels.
no code implementations • ICLR 2020 • Duc Tam Nguyen, Chaithanya Kumar Mummadi, Thi Phuong Nhung Ngo, Thi Hoai Phuong Nguyen, Laura Beggel, Thomas Brox
Deep neural networks (DNNs) have been shown to over-fit a dataset when being trained with noisy labels for a long enough time.
no code implementations • 28 Sep 2019 • Duc Tam Nguyen, Maximilian Dax, Chaithanya Kumar Mummadi, Thi Phuong Nhung Ngo, Thi Hoai Phuong Nguyen, Zhongyu Lou, Thomas Brox
Alternative unsupervised approaches rely on careful selection of multiple handcrafted saliency methods to generate noisy pseudo-ground-truth labels.
no code implementations • 9 Aug 2019 • Chaithanya Kumar Mummadi, Tim Genewein, Dan Zhang, Thomas Brox, Volker Fischer
We achieve state-of-the-art pruning results for ResNet-50 with higher accuracy on ImageNet.
no code implementations • ICCV 2019 • Chaithanya Kumar Mummadi, Thomas Brox, Jan Hendrik Metzen
Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space.