no code implementations • 27 Feb 2024 • Ram J. Zaveri, Voke Brume, Gianfranco Doretto
Microscopy data collections are becoming larger and more frequent.
no code implementations • 22 Nov 2023 • Colleen Farrelly, Yashbir Singh, Quincy A. Hathaway, Gunnar Carlsson, Ashok Choudhary, Rahul Paul, Gianfranco Doretto, Yassine Himeur, Shadi Atalls, Wathiq Mansoor
Institutional bias can impact patient outcomes, educational attainment, and legal system navigation.
no code implementations • 1 Nov 2023 • Thinh Phan, Khoa Vo, Duy Le, Gianfranco Doretto, Donald Adjeroh, Ngan Le
Temporal action detection (TAD) involves the localization and classification of action instances within untrimmed videos.
1 code implementation • 5 Oct 2023 • Kashu Yamazaki, Taisei Hanyu, Khoa Vo, Thang Pham, Minh Tran, Gianfranco Doretto, Anh Nguyen, Ngan Le
Open-Fusion harnesses the power of a pre-trained vision-language foundation model (VLFM) for open-set semantic comprehension and employs the Truncated Signed Distance Function (TSDF) for swift 3D scene reconstruction.
2 code implementations • 7 Sep 2023 • Nhat-Tan Bui, Dinh-Hieu Hoang, Minh-Triet Tran, Gianfranco Doretto, Donald Adjeroh, Brijesh Patel, Arabinda Choudhary, Ngan Le
Image segmentation remains a pivotal component in medical image analysis, aiding in the extraction of critical information for precise diagnostic practices.
no code implementations • 19 Aug 2023 • Tiehang Duan, Zhenyi Wang, Gianfranco Doretto, Fang Li, Cui Tao, Donald Adjeroh
In this work, we propose a principled approach to perform dynamic evolution on the data for improvement of decoding robustness.
1 code implementation • 9 Jul 2023 • Salman Mohamadi, Ghulam Mujtaba, Ngan Le, Gianfranco Doretto, Donald A. Adjeroh
We also lay out essential foundational literature on LLMs and GAI in general and their connection with ChatGPT.
no code implementations • 2 Jul 2023 • Salman Mohamadi, Gianfranco Doretto, Donald A. Adjeroh
This paper is a fundamental work where, we investigate role of mutual information in SSL, and reformulate the problem of SSL in the context of a new perspective on mutual information.
no code implementations • 6 Jun 2023 • Ranya Almohsen, Shivang Patel, Donald A. Adjeroh, Gianfranco Doretto
While this is a known problem that has been studied in recent years for the case of supervised learning, the case of novelty detection has received very limited attention.
no code implementations • 2 Jun 2023 • Marcela Mera-Trujillo, Shivang Patel, Yu Gu, Gianfranco Doretto
Keypoint detection and matching is a fundamental task in many computer vision problems, from shape reconstruction, to structure from motion, to AR/VR applications and robotics.
no code implementations • 28 May 2023 • Kim Hoang Tran, Anh Duy Le Dinh, Tien Phat Nguyen, Thinh Phan, Pha Nguyen, Khoa Luu, Donald Adjeroh, Gianfranco Doretto, Ngan Hoang Le
Our contributions are benchmarked through extensive experiments conducted on the Referring GMOT dataset for GMOT task.
no code implementations • 28 Dec 2022 • Zaigham Randhawa, Shivang Patel, Donald Adjeroh, Gianfranco Doretto
The pandemic of these very recent years has led to a dramatic increase in people wearing protective masks in public venues.
no code implementations • 28 Dec 2022 • Matthew Keaton, Ram Zaveri, Gianfranco Doretto
Automated cellular instance segmentation is a process utilized for accelerating biological research for the past two decades, and recent advancements have produced higher quality results with less effort from the biologist.
no code implementations • 28 Dec 2022 • Sinan Sabri, Zaigham Randhawa, Gianfranco Doretto
Person re-identification is a challenging task because of the high intra-class variance induced by the unrestricted nuisance factors of variations such as pose, illumination, viewpoint, background, and sensor noise.
no code implementations • 28 Oct 2022 • Salman Mohamadi, Gianfranco Doretto, Donald A. Adjeroh
This double supervision approach is captured in two key steps: 1) invariance enforcement to data augmentation, and 2) fuzzy pseudo labeling (both hard and soft annotation).
no code implementations • 11 Oct 2022 • Salman Mohamadi, Gianfranco Doretto, Donald A. Adjeroh
We show empirical results of our framework, and comparative performance with the state-of-the-art on four datasets, namely, MNIST, CIFAR10, CIFAR100 and ImageNet to establish a new baseline in two different settings.
1 code implementation • 3 Jun 2021 • Matthew R. Keaton, Ram J. Zaveri, Meghana Kovur, Cole Henderson, Donald A. Adjeroh, Gianfranco Doretto
Plant species identification in the wild is a difficult problem in part due to the high variability of the input data, but also because of complications induced by the long-tail effects of the datasets distribution.
12 code implementations • CVPR 2020 • Stanislav Pidhorskyi, Donald Adjeroh, Gianfranco Doretto
We designed two autoencoders: one based on a MLP encoder, and another based on a StyleGAN generator, which we call StyleALAE.
Ranked #5 on Image Generation on CelebA 256x256 (FID metric)
1 code implementation • NeurIPS 2018 • Stanislav Pidhorskyi, Ranya Almohsen, Donald A. Adjeroh, Gianfranco Doretto
We assume that training data is available to describe only the inlier distribution.
no code implementations • 23 Apr 2018 • Stanislav Pidhorskyi, Michael Morehead, Quinn Jones, George Spirou, Gianfranco Doretto
The quest for deeper understanding of biological systems has driven the acquisition of increasingly larger multidimensional image datasets.
no code implementations • NeurIPS 2017 • Saeid Motiian, Quinn Jones, Seyed Mehdi Iranmanesh, Gianfranco Doretto
This work provides a framework for addressing the problem of supervised domain adaptation with deep models.
3 code implementations • ICCV 2017 • Saeid Motiian, Marco Piccirilli, Donald A. Adjeroh, Gianfranco Doretto
This work provides a unified framework for addressing the problem of visual supervised domain adaptation and generalization with deep models.
Ranked #87 on Domain Generalization on PACS
no code implementations • CVPR 2016 • Saeid Motiian, Marco Piccirilli, Donald A. Adjeroh, Gianfranco Doretto
The problem is challenging because of the intrinsic asymmetry caused by the missing auxiliary view during testing.
no code implementations • ICCV 2015 • Farzad Siyahjani, Ranya Almohsen, Sinan Sabri, Gianfranco Doretto
Sparse representation and low-rank matrix decomposition approaches have been successfully applied to several computer vision problems.