no code implementations • 8 Apr 2024 • Saman Motamed, Wouter Van Gansbeke, Luc van Gool
With recent advances in image and video diffusion models for content creation, a plethora of techniques have been proposed for customizing their generated content.
no code implementations • 1 Apr 2024 • Reni Paskaleva, Mykyta Holubakha, Andela Ilic, Saman Motamed, Luc van Gool, Danda Paudel
However, emotions are often compound, e. g. happily surprised, and can be mapped to the action units (AUs) used for expressing emotions, and trivially to the canonical ones.
1 code implementation • 10 Jan 2024 • Lin Zhang, Linghan Xu, Saman Motamed, Shayok Chakraborty, Fernando de la Torre
Unsupervised domain adaptation (UDA) for image classification has made remarkable progress in transferring classification knowledge from a labeled source domain to an unlabeled target domain, thanks to effective domain alignment techniques.
no code implementations • 6 Dec 2023 • Jianjin Xu, Saman Motamed, Praneetha Vaddamanu, Chen Henry Wu, Christian Haene, Jean-Charles Bazin, Fernando de la Torre
Specifically, we insert parallel attention matrices to each cross-attention module in the denoising network, which attends to features extracted from reference images by an identity encoder.
no code implementations • 23 Nov 2023 • Saman Motamed, Danda Pani Paudel, Luc van Gool
To enable customized content creation based on a few example images of a concept, methods such as Textual Inversion and DreamBooth invert the desired concept and enable synthesizing it in new scenes.
2 code implementations • ICCV 2023 • Saman Motamed, Jianjin Xu, Chen Henry Wu, Fernando de la Torre
By using ~40 reference images, PATMAT creates anchor points in MAT's style module, and tunes the model using the fixed anchors to adapt the model to a new face identity.
1 code implementation • 14 Sep 2022 • Chen Henry Wu, Saman Motamed, Shaunak Srivastava, Fernando de la Torre
Our experiments demonstrate how PromptGen can efficiently sample from several unconditional generative models (e. g., StyleGAN2, StyleNeRF, diffusion autoencoder, NVAE) in a controlled or/and de-biased manner using various off-the-shelf models: (1) with the CLIP model as control, PromptGen can sample images guided by text, (2) with image classifiers as control, PromptGen can de-bias generative models across a set of attributes or attribute combinations, and (3) with inverse graphics models as control, PromptGen can sample images of the same identity in different poses.
no code implementations • 3 Mar 2021 • Saman Motamed, Farzad Khalvati
By training a weak GAN and using its generated output image parallel to the regular GAN, the Vanishing Twin training improves semi-supervised image classification where image similarity can hurt classification tasks.
no code implementations • 13 Feb 2021 • Saman Motamed, Farzad Khalvati
We propose a modification to the traditional training of GANs that allows for improved multi-class classification in similar classes of images in a semi-supervised learning framework.
1 code implementation • 6 Oct 2020 • Saman Motamed, Patrik Rogalla, Farzad Khalvati
Gathering labeled data is a cumbersome task and requires time and resources which could further strain health care systems and radiologists at the early stages of a pandemic such as COVID-19.
no code implementations • 5 Jun 2020 • Saman Motamed, Patrik Rogalla, Farzad Khalvati
Data Augmentation techniques improve the generalizability of neural networks by using existing training data more effectively.
no code implementations • 20 Sep 2019 • Saman Motamed, Isha Gujrathi, Dominik Deniffel, Anton Oentoro, Masoom A. Haider, Farzad Khalvati
Using a fine-tuning data of 115 patients from the target domain, dice score coefficient of 0. 85 and 0. 84 are achieved for segmentation of whole gland and transition zone, respectively, in the target domain.