no code implementations • 21 Dec 2023 • Nazmul Karim, Umar Khalid, Hasan Iqbal, Jing Hua, Chen Chen
To date, editing 3D scenes requires either re-training the model to adapt to various 3D edited scenes or design-specific methods for each special editing type.
1 code implementation • 14 Dec 2023 • Umar Khalid, Hasan Iqbal, Nazmul Karim, Jing Hua, Chen Chen
Our approach achieves faster editing speeds and superior output quality compared to existing 3D editing models, bridging the gap between textual instructions and high-quality 3D scene editing in latent space.
1 code implementation • 29 Aug 2023 • Umar Khalid, Hasan Iqbal, Saeed Vahidian, Jing Hua, Chen Chen
Machine learning plays a vital role in industrial HRI by enhancing the adaptability and autonomy of robots in complex environments.
1 code implementation • 30 Jun 2023 • Nazmul Karim, Abdullah Al Arafat, Umar Khalid, Zhishan Guo, Naznin Rahnavard
Extensive experiments show that the proposed method achieves state-of-the-art performance on a wide range of backdoor defense benchmarks: four different datasets- CIFAR10, GTSRB, Tiny-ImageNet, and ImageNet; 13 recent backdoor attacks, e. g.
1 code implementation • 31 May 2023 • Hasan Iqbal, Umar Khalid, Jing Hua, Chen Chen
It can be challenging to identify brain MRI anomalies using supervised deep-learning techniques due to anatomical heterogeneity and the requirement for pixel-level labeling.
1 code implementation • 30 May 2023 • Nazmul Karim, Umar Khalid, Mohsen Joneidi, Chen Chen, Nazanin Rahnavard
Text-to-Image (T2I) diffusion models have achieved remarkable success in synthesizing high-quality images conditioned on text prompts.
no code implementations • 4 Oct 2022 • Guangyu Sun, Umar Khalid, Matias Mendieta, Taojiannan Yang, Chen Chen
Recently, the use of small pre-trained models has been shown effective in federated learning optimization and improving convergence.
1 code implementation • 21 Apr 2022 • Nazmul Karim, Umar Khalid, Ashkan Esmaeili, Nazanin Rahnavard
After purification, we perform fine-tuning in a semi-supervised fashion that ensures the participation of all available samples.
no code implementations • 19 Apr 2022 • Addel Zafar, Umar Khalid
We also show qualitative results for object attribute prediction on unseen objects, which demonstrate the effectiveness of our approach for describing unknown objects.
1 code implementation • 6 Apr 2022 • Umar Khalid, Nazmul Karim, Nazanin Rahnavard
Deep neural networks (DNNs) designed for computer vision and natural language processing tasks cannot be directly applied to the radio frequency (RF) datasets.
1 code implementation • 6 Apr 2022 • Umar Khalid, Ashkan Esmaeili, Nazmul Karim, Nazanin Rahnavard
The method proposed in this work referred to as RODD outperforms SOTA detection performance on an extensive suite of benchmark datasets on OOD detection tasks.
Ranked #1 on Out-of-Distribution Detection on cifar100 (using extra training data)
no code implementations • 9 Oct 2021 • Nazmul Karim, Umar Khalid, Nick Meeker, Sarinda Samarasinghe
Through comparing adversarial robustness achieved without adversarial training, with triplet loss adversarial training, and our contrastive pre-training combined with triplet loss adversarial fine-tuning, we find that our method achieves comparable results with far fewer epochs re-quired during fine-tuning.
no code implementations • 13 Jun 2021 • Ashkan Esmaeili, Mohsen Joneidi, Mehrdad Salimitari, Umar Khalid, Nazanin Rahnavard
The problem of simultaneous column and row subset selection is addressed in this paper.