16 citations · 37 across the 15 of their papers we have counts for
14 papers · 1 filter
PSF-4D: A Progressive Sampling Framework for View Consistent 4D Editing
Hasan Iqbal, Nazmul Karim, Umar Khalid +4
Instruction-guided generative models, especially those using text-to-image (T2I) and text-to-video (T2V) diffusion frameworks, have advanced the field of content editing in recent…
Fisher Information guided Purification against Backdoor Attacks
Nazmul Karim, Abdullah Al Arafat, Adnan Siraj Rakin +2
Studies on backdoor attacks in recent years suggest that an adversary can compromise the integrity of a deep neural network (DNN) by manipulating a small set of training samples. O…
Augmented Neural Fine-Tuning for Efficient Backdoor Purification
Nazmul Karim, Abdullah Al Arafat, Umar Khalid +2
Recent studies have revealed the vulnerability of deep neural networks (DNNs) to various backdoor attacks, where the behavior of DNNs can be compromised by utilizing certain types…
Free-Editor: Zero-shot Text-driven 3D Scene Editing
Nazmul Karim, Hasan Iqbal, Umar Khalid +2
Text-to-Image (T2I) diffusion models have recently gained traction for their versatility and user-friendliness in 2D content generation and editing. However, training a diffusion m…
LatentEditor: Text Driven Local Editing of 3D Scenes
Umar Khalid, Hasan Iqbal, Nazmul Karim +2
While neural fields have made significant strides in view synthesis and scene reconstruction, editing them poses a formidable challenge due to their implicit encoding of geometry a…
Efficient Backdoor Removal Through Natural Gradient Fine-tuning
Nazmul Karim, Abdullah Al Arafat, Umar Khalid +2
The success of a deep neural network (DNN) heavily relies on the details of the training scheme; e.g., training data, architectures, hyper-parameters, etc. Recent backdoor attacks…
SAVE: Spectral-Shift-Aware Adaptation of Image Diffusion Models for Text-driven Video Editing
Nazmul Karim, Umar Khalid, Mohsen Joneidi +2
Text-to-Image (T2I) diffusion models have achieved remarkable success in synthesizing high-quality images conditioned on text prompts. Recent methods have tried to replicate the su…
C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation
Nazmul Karim, Niluthpol Chowdhury Mithun, Abhinav Rajvanshi +3
Unsupervised domain adaptation (UDA) approaches focus on adapting models trained on a labeled source domain to an unlabeled target domain. UDA methods have a strong assumption that…
UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learning
Nazmul Karim, Mamshad Nayeem Rizve, Nazanin Rahnavard +2
Supervised deep learning methods require a large repository of annotated data; hence, label noise is inevitable. Training with such noisy data negatively impacts the generalization…
CNLL: A Semi-supervised Approach For Continual Noisy Label Learning
Nazmul Karim, Umar Khalid, Ashkan Esmaeili +1
The task of continual learning requires careful design of algorithms that can tackle catastrophic forgetting. However, the noisy label, which is inevitable in a real-world scenario…
RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection
Umar Khalid, Ashkan Esmaeili, Nazmul Karim +1
Recent studies have addressed the concern of detecting and rejecting the out-of-distribution (OOD) samples as a major challenge in the safe deployment of deep learning (DL) models.…
Adversarial Training for Face Recognition Systems using Contrastive Adversarial Learning and Triplet Loss Fine-tuning
Nazmul Karim, Umar Khalid, Nick Meeker +1
Though much work has been done in the domain of improving the adversarial robustness of facial recognition systems, a surprisingly small percentage of it has focused on self-superv…
SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network
Nazmul Karim, Nazanin Rahnavard
Single-pixel imaging is a novel imaging scheme that has gained popularity due to its huge computational gain and potential for a low-cost alternative to imaging beyond the visible…
Odyssey: Creation, Analysis and Detection of Trojan Models
Marzieh Edraki, Nazmul Karim, Nazanin Rahnavard +2
Along with the success of deep neural network (DNN) models, rise the threats to the integrity of these models. A recent threat is the Trojan attack where an attacker interferes wit…