no code implementations • ICLR 2019 • Saeid Asgari Taghanaki, Shekoofeh Azizi, Ghassan Hamarneh
The linear and non-flexible nature of deep convolutional models makes them vulnerable to carefully crafted adversarial perturbations.
no code implementations • 27 Mar 2024 • Saeid Asgari Taghanaki, Joseph Lambourne
The advent of generative AI models has revolutionized digital content creation, yet it introduces challenges in maintaining copyright integrity due to generative parroting, where models mimic their training data too closely.
1 code implementation • 6 Sep 2023 • Aliasghar Khani, Saeid Asgari Taghanaki, Aditya Sanghi, Ali Mahdavi Amiri, Ghassan Hamarneh
Then, using the extracted attention maps, the text embeddings of Stable Diffusion are optimized such that, each of them, learn about a single segmented region from the training image.
no code implementations • 1 Sep 2023 • Saeid Asgari Taghanaki, Aliasghar Khani, Ali Saheb Pasand, Amir Khasahmadi, Aditya Sanghi, Karl D. D. Willis, Ali Mahdavi-Amiri
These sentences are then used to extract the most frequent words, providing a comprehensive understanding of the learned features and patterns within the classifier.
no code implementations • 8 Jul 2023 • Aditya Sanghi, Pradeep Kumar Jayaraman, Arianna Rampini, Joseph Lambourne, Hooman Shayani, Evan Atherton, Saeid Asgari Taghanaki
Significant progress has recently been made in creative applications of large pre-trained models for downstream tasks in 3D vision, such as text-to-shape generation.
1 code implementation • 30 Sep 2022 • Saeid Asgari Taghanaki, Aliasghar Khani, Fereshte Khani, Ali Gholami, Linh Tran, Ali Mahdavi-Amiri, Ghassan Hamarneh
A fundamental challenge of over-parameterized deep learning models is learning meaningful data representations that yield good performance on a downstream task without over-fitting spurious input features.
no code implementations • 4 Jul 2022 • Saeid Asgari Taghanaki, Ali Gholami, Fereshte Khani, Kristy Choi, Linh Tran, Ran Zhang, Aliasghar Khani
Batch normalization (BN) is a ubiquitous technique for training deep neural networks that accelerates their convergence to reach higher accuracy.
no code implementations • 11 Jun 2021 • Saeid Asgari Taghanaki, Kristy Choi, Amir Khasahmadi, Anirudh Goyal
A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream task, without overfitting to spurious input features.
1 code implementation • 23 Nov 2020 • Saeid Asgari Taghanaki, Jieliang Luo, Ran Zhang, Ye Wang, Pradeep Kumar Jayaraman, Krishna Murthy Jatavallabhula
We also find that robustness to unseen transformations cannot be brought about merely by extensive data augmentation.
1 code implementation • 9 Jul 2020 • Saeid Asgari Taghanaki, Kaveh Hassani, Pradeep Kumar Jayaraman, Amir Hosein Khasahmadi, Tonya Custis
We show that coupling a PointMask layer with an arbitrary model can discern the points in the input space which contribute the most to the prediction score, thereby leading to interpretability.
no code implementations • 12 May 2020 • Saeid Asgari Taghanaki, Mohammad Havaei, Alex Lamb, Aditya Sanghi, Ara Danielyan, Tonya Custis
The latent variables learned by VAEs have seen considerable interest as an unsupervised way of extracting features, which can then be used for downstream tasks.
no code implementations • 16 Nov 2019 • Saeid Asgari Taghanaki, Kumar Abhishek, Ghassan Hamarneh
To test the effectiveness of the proposed idea and compare it with other competing methods, we design several test scenarios, such as classification performance, uncertainty, out-of-distribution, and robustness analyses.
no code implementations • 16 Oct 2019 • Saeid Asgari Taghanaki, Kumar Abhishek, Joseph Paul Cohen, Julien Cohen-Adad, Ghassan Hamarneh
The semantic image segmentation task consists of classifying each pixel of an image into an instance, where each instance corresponds to a class.
no code implementations • 28 Mar 2019 • Saeid Asgari Taghanaki, Mohammad Havaei, Tess Berthier, Francis Dutil, Lisa Di Jorio, Ghassan Hamarneh, Yoshua Bengio
The scarcity of richly annotated medical images is limiting supervised deep learning based solutions to medical image analysis tasks, such as localizing discriminatory radiomic disease signatures.
1 code implementation • CVPR 2019 • Saeid Asgari Taghanaki, Kumar Abhishek, Shekoofeh Azizi, Ghassan Hamarneh
The linear and non-flexible nature of deep convolutional models makes them vulnerable to carefully crafted adversarial perturbations.
no code implementations • 9 Jul 2018 • Saeid Asgari Taghanaki, Arkadeep Das, Ghassan Hamarneh
Recently, there have been several successful deep learning approaches for automatically classifying chest X-ray images into different disease categories.
1 code implementation • 8 May 2018 • Saeid Asgari Taghanaki, Yefeng Zheng, S. Kevin Zhou, Bogdan Georgescu, Puneet Sharma, Daguang Xu, Dorin Comaniciu, Ghassan Hamarneh
The output imbalance refers to the imbalance between the false positives and false negatives of the inference model.
no code implementations • 14 Apr 2018 • Saeid Asgari Taghanaki, Aicha Bentaieb, Anmol Sharma, S. Kevin Zhou, Yefeng Zheng, Bogdan Georgescu, Puneet Sharma, Sasa Grbic, Zhoubing Xu, Dorin Comaniciu, Ghassan Hamarneh
Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risks for vanishing gradients.