Search Results for author: Mehrdad Saberi

Found 6 papers, 4 papers with code

Understanding and Mitigating Compositional Issues in Text-to-Image Generative Models

1 code implementation12 Jun 2024 Arman Zarei, Keivan Rezaei, Samyadeep Basu, Mehrdad Saberi, Mazda Moayeri, Priyatham Kattakinda, Soheil Feizi

We also show that re-weighting the erroneous attention contributions in CLIP can also lead to improved compositional performances, however these improvements are often less significant than those achieved by solely learning a linear projection head, highlighting erroneous attentions to be only a minor error source.

Image Generation

DREW : Towards Robust Data Provenance by Leveraging Error-Controlled Watermarking

1 code implementation5 Jun 2024 Mehrdad Saberi, Vinu Sankar Sadasivan, Arman Zarei, Hessam Mahdavifar, Soheil Feizi

Identifying the origin of data is crucial for data provenance, with applications including data ownership protection, media forensics, and detecting AI-generated content.

Retrieval

EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods

no code implementations3 Oct 2023 Samyadeep Basu, Mehrdad Saberi, Shweta Bhardwaj, Atoosa Malemir Chegini, Daniela Massiceti, Maziar Sanjabi, Shell Xu Hu, Soheil Feizi

From both the human study and automated evaluation, we find that: (i) Instruct-Pix2Pix, Null-Text and SINE are the top-performing methods averaged across different edit types, however {\it only} Instruct-Pix2Pix and Null-Text are able to preserve original image properties; (ii) Most of the editing methods fail at edits involving spatial operations (e. g., changing the position of an object).

Benchmarking text-guided-image-editing

PRIME: Prioritizing Interpretability in Failure Mode Extraction

no code implementations29 Sep 2023 Keivan Rezaei, Mehrdad Saberi, Mazda Moayeri, Soheil Feizi

To improve on these shortcomings, we propose a novel approach that prioritizes interpretability in this problem: we start by obtaining human-understandable concepts (tags) of images in the dataset and then analyze the model's behavior based on the presence or absence of combinations of these tags.

Image Classification

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

1 code implementation29 Sep 2023 Mehrdad Saberi, Vinu Sankar Sadasivan, Keivan Rezaei, Aounon Kumar, Atoosa Chegini, Wenxiao Wang, Soheil Feizi

Moreover, we show that watermarking methods are vulnerable to spoofing attacks where the attacker aims to have real images identified as watermarked ones, damaging the reputation of the developers.

Adversarial Attack Face Swapping

ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training

1 code implementation29 Mar 2021 Zeinab Golgooni, Mehrdad Saberi, Masih Eskandar, Mohammad Hossein Rohban

Making deep neural networks robust to small adversarial noises has recently been sought in many applications.

Cannot find the paper you are looking for? You can Submit a new open access paper.