Umar Khalid

Umar Khalid, Hasan Iqbal, Saeed Vahidian et al.

Human-robot interaction (HRI) is a rapidly growing field that encompasses social and industrial applications. Machine learning plays a vital role in industrial HRI by enhancing the adaptability and autonomy of robots in complex environments. However, data privacy is a crucial concern in the interaction between humans and robots, as companies need to protect sensitive data while machine learning algorithms require access to large datasets. Federated Learning (FL) offers a solution by enabling the distributed training of models without sharing raw data. Despite extensive research on Federated learning (FL) for tasks such as natural language processing (NLP) and image classification, the question of how to use FL for HRI remains an open research problem. The traditional FL approach involves transmitting large neural network parameter matrices between the server and clients, which can lead to high communication costs and often becomes a bottleneck in FL. This paper proposes a communication-efficient FL framework for human-robot interaction (CEFHRI) to address the challenges of data heterogeneity and communication costs. The framework leverages pre-trained models and introduces a trainable spatiotemporal adapter for video understanding tasks in HRI. Experimental results on three human-robot interaction benchmark datasets: HRI30, InHARD, and COIN demonstrate the superiority of CEFHRI over full fine-tuning in terms of communication costs. The proposed methodology provides a secure and efficient approach to HRI federated learning, particularly in industrial environments with data privacy concerns and limited communication bandwidth. Our code is available at https://github.com/umarkhalidAI/CEFHRI-Efficient-Federated-Learning.

Umar Khalid, Ashkan Esmaeili, Nazmul Karim et al.

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. It is desired that the DL model should only be confident about the in-distribution (ID) data which reinforces the driving principle of the OOD detection. In this paper, we propose a simple yet effective generalized OOD detection method independent of out-of-distribution datasets. Our approach relies on self-supervised feature learning of the training samples, where the embeddings lie on a compact low-dimensional space. Motivated by the recent studies that show self-supervised adversarial contrastive learning helps robustify the model, we empirically show that a pre-trained model with self-supervised contrastive learning yields a better model for uni-dimensional feature learning in the latent space. 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. On the CIFAR-100 benchmarks, RODD achieves a 26.97 $\%$ lower false-positive rate (FPR@95) compared to SOTA methods.

Nazmul Karim, Umar Khalid, Ashkan Esmaeili et al.

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, seems to exacerbate the situation. While very few studies have addressed the issue of continual learning under noisy labels, long training time and complicated training schemes limit their applications in most cases. In contrast, we propose a simple purification technique to effectively cleanse the online data stream that is both cost-effective and more accurate. After purification, we perform fine-tuning in a semi-supervised fashion that ensures the participation of all available samples. Training in this fashion helps us learn a better representation that results in state-of-the-art (SOTA) performance. Through extensive experimentation on 3 benchmark datasets, MNIST, CIFAR10 and CIFAR100, we show the effectiveness of our proposed approach. We achieve a 24.8% performance gain for CIFAR10 with 20% noise over previous SOTA methods. Our code is publicly available.

Guangyu Sun, Umar Khalid, Matias Mendieta et al.

Federated learning (FL) has emerged as a promising paradigm for enabling the collaborative training of models without centralized access to the raw data on local devices. In the typical FL paradigm (e.g., FedAvg), model weights are sent to and from the server each round to participating clients. Recently, the use of small pre-trained models has been shown to be effective in federated learning optimization and improving convergence. However, recent state-of-the-art pre-trained models are getting more capable but also have more parameters, known as the "Foundation Models." In conventional FL, sharing the enormous model weights can quickly put a massive communication burden on the system, especially if more capable models are employed. Can we find a solution to enable those strong and readily available pre-trained models in FL to achieve excellent performance while simultaneously reducing the communication burden? To this end, we investigate the use of parameter-efficient fine-tuning in federated learning and thus introduce a new framework: FedPEFT. Specifically, we systemically evaluate the performance of FedPEFT across a variety of client stability, data distribution, and differential privacy settings. By only locally tuning and globally sharing a small portion of the model weights, significant reductions in the total communication overhead can be achieved while maintaining competitive or even better performance in a wide range of federated learning scenarios, providing insight into a new paradigm for practical and effective federated systems.

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. To address this challenge, we propose to convert the raw RF data to data types that are suitable for off-the-shelf DNNs by introducing a convolutional transform technique. In addition, we propose a simple 5-layer convolutional neural network architecture (CONV-5) that can operate with raw RF I/Q data without any transformation. Further, we put forward an RF dataset, referred to as RF1024, to facilitate future RF research. RF1024 consists of 8 different RF modulation classes with each class having 1000/200 training/test samples. Each sample of the RF1024 dataset contains 1024 complex I/Q values. Lastly, the experiments are performed on the RadioML2016 and RF1024 datasets to demonstrate the improved classification performance.

Nazmul Karim, Abdullah Al Arafat, Umar Khalid et al.

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 suggest that an adversary can take advantage of such training details and compromise the integrity of a DNN. Our studies show that a backdoor model is usually optimized to a bad local minima, i.e. sharper minima as compared to a benign model. Intuitively, a backdoor model can be purified by reoptimizing the model to a smoother minima through fine-tuning with a few clean validation data. However, fine-tuning all DNN parameters often requires huge computational costs and often results in sub-par clean test performance. To address this concern, we propose a novel backdoor purification technique, Natural Gradient Fine-tuning (NGF), which focuses on removing the backdoor by fine-tuning only one layer. Specifically, NGF utilizes a loss surface geometry-aware optimizer that can successfully overcome the challenge of reaching a smooth minima under a one-layer optimization scenario. To enhance the generalization performance of our proposed method, we introduce a clean data distribution-aware regularizer based on the knowledge of loss surface curvature matrix, i.e., Fisher Information Matrix. 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. Blend, Dynamic, WaNet, ISSBA, etc.

Nazmul Karim, Abdullah Al Arafat, Umar Khalid et al.

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 of triggers or poisoning mechanisms. State-of-the-art (SOTA) defenses employ too-sophisticated mechanisms that require either a computationally expensive adversarial search module for reverse-engineering the trigger distribution or an over-sensitive hyper-parameter selection module. Moreover, they offer sub-par performance in challenging scenarios, e.g., limited validation data and strong attacks. In this paper, we propose Neural mask Fine-Tuning (NFT) with an aim to optimally re-organize the neuron activities in a way that the effect of the backdoor is removed. Utilizing a simple data augmentation like MixUp, NFT relaxes the trigger synthesis process and eliminates the requirement of the adversarial search module. Our study further reveals that direct weight fine-tuning under limited validation data results in poor post-purification clean test accuracy, primarily due to overfitting issue. To overcome this, we propose to fine-tune neural masks instead of model weights. In addition, a mask regularizer has been devised to further mitigate the model drift during the purification process. The distinct characteristics of NFT render it highly efficient in both runtime and sample usage, as it can remove the backdoor even when a single sample is available from each class. We validate the effectiveness of NFT through extensive experiments covering the tasks of image classification, object detection, video action recognition, 3D point cloud, and natural language processing. We evaluate our method against 14 different attacks (LIRA, WaNet, etc.) on 11 benchmark data sets such as ImageNet, UCF101, Pascal VOC, ModelNet, OpenSubtitles2012, etc.

Umar Khalid, Hasan Iqbal, Azib Farooq et al.

We introduce 3DEgo to address a novel problem of directly synthesizing photorealistic 3D scenes from monocular videos guided by textual prompts. Conventional methods construct a text-conditioned 3D scene through a three-stage process, involving pose estimation using Structure-from-Motion (SfM) libraries like COLMAP, initializing the 3D model with unedited images, and iteratively updating the dataset with edited images to achieve a 3D scene with text fidelity. Our framework streamlines the conventional multi-stage 3D editing process into a single-stage workflow by overcoming the reliance on COLMAP and eliminating the cost of model initialization. We apply a diffusion model to edit video frames prior to 3D scene creation by incorporating our designed noise blender module for enhancing multi-view editing consistency, a step that does not require additional training or fine-tuning of T2I diffusion models. 3DEgo utilizes 3D Gaussian Splatting to create 3D scenes from the multi-view consistent edited frames, capitalizing on the inherent temporal continuity and explicit point cloud data. 3DEgo demonstrates remarkable editing precision, speed, and adaptability across a variety of video sources, as validated by extensive evaluations on six datasets, including our own prepared GS25 dataset. Project Page: https://3dego.github.io/

Addel Zafar, Umar Khalid

Traditional object detection answers two questions; "what" (what the object is?) and "where" (where the object is?). "what" part of the object detection can be fine-grained further i.e. "what type", "what shape" and "what material" etc. This results in the shifting of the object detection tasks to the object description paradigm. Describing an object provides additional detail that enables us to understand the characteristics and attributes of the object ("plastic boat" not just boat, "glass bottle" not just bottle). This additional information can implicitly be used to gain insight into unseen objects (e.g. unknown object is "metallic", "has wheels"), which is not possible in traditional object detection. In this paper, we present a new approach to simultaneously detect objects and infer their attributes, we call it Detect and Describe (DaD) framework. DaD is a deep learning-based approach that extends object detection to object attribute prediction as well. We train our model on aPascal train set and evaluate our approach on aPascal test set. We achieve 97.0% in Area Under the Receiver Operating Characteristic Curve (AUC) for object attributes prediction on aPascal test set. We also show qualitative results for object attribute prediction on unseen objects, which demonstrate the effectiveness of our approach for describing unknown objects.

Hasan Iqbal, Umar Khalid, Jing Hua et al.

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. Unsupervised anomaly detection approaches provide an alternative solution by relying only on sample-level labels of healthy brains to generate a desired representation to identify abnormalities at the pixel level. Although, generative models are crucial for generating such anatomically consistent representations of healthy brains, accurately generating the intricate anatomy of the human brain remains a challenge. In this study, we present a method called masked-DDPM (mDPPM), which introduces masking-based regularization to reframe the generation task of diffusion models. Specifically, we introduce Masked Image Modeling (MIM) and Masked Frequency Modeling (MFM) in our self-supervised approach that enables models to learn visual representations from unlabeled data. To the best of our knowledge, this is the first attempt to apply MFM in DPPM models for medical applications. We evaluate our approach on datasets containing tumors and numerous sclerosis lesions and exhibit the superior performance of our unsupervised method as compared to the existing fully/weakly supervised baselines. Code is available at https://github.com/hasan1292/mDDPM.

Amna Khalid, Ayma Khalid, Umar Khalid

The application of large language models (LLMs) in healthcare has gained significant attention due to their ability to process complex medical data and provide insights for clinical decision-making. These models have demonstrated substantial capabilities in understanding and generating natural language, which is crucial for medical documentation, diagnostics, and patient interaction. This review examines the trajectory of language models from their early stages to the current state-of-the-art LLMs, highlighting their strengths in healthcare applications and discussing challenges such as data privacy, bias, and ethical considerations. The potential of LLMs to enhance healthcare delivery is explored, alongside the necessary steps to ensure their ethical and effective integration into medical practice.

Umar Khalid, Hasan Iqbal, Nazmul Karim et al.

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 and texture information from multi-view inputs. In this paper, we introduce \textsc{LatentEditor}, an innovative framework designed to empower users with the ability to perform precise and locally controlled editing of neural fields using text prompts. Leveraging denoising diffusion models, we successfully embed real-world scenes into the latent space, resulting in a faster and more adaptable NeRF backbone for editing compared to traditional methods. To enhance editing precision, we introduce a delta score to calculate the 2D mask in the latent space that serves as a guide for local modifications while preserving irrelevant regions. Our novel pixel-level scoring approach harnesses the power of InstructPix2Pix (IP2P) to discern the disparity between IP2P conditional and unconditional noise predictions in the latent space. The edited latents conditioned on the 2D masks are then iteratively updated in the training set to achieve 3D local editing. 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. We show the superiority of our approach on four benchmark 3D datasets, LLFF, IN2N, NeRFStudio and NeRF-Art. Project Page: https://latenteditor.github.io/

Nazmul Karim, Hasan Iqbal, Umar Khalid et al.

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 model specifically for 3D scene editing is challenging due to the scarcity of large-scale datasets. Currently, editing 3D scenes necessitates either retraining the model to accommodate various 3D edits or developing specific methods tailored to each unique editing type. Moreover, state-of-the-art (SOTA) techniques require multiple synchronized edited images from the same scene to enable effective scene editing. Given the current limitations of T2I models, achieving consistent editing effects across multiple images remains difficult, leading to multi-view inconsistency in editing. This inconsistency undermines the performance of 3D scene editing when these images are utilized. In this study, we introduce a novel, training-free 3D scene editing technique called \textsc{Free-Editor}, which enables users to edit 3D scenes without the need for model retraining during the testing phase. Our method effectively addresses the issue of multi-view style inconsistency found in state-of-the-art (SOTA) methods through the implementation of a single-view editing scheme. Specifically, we demonstrate that editing a particular 3D scene can be achieved by modifying only a single view. To facilitate this, we present an Edit Transformer that ensures intra-view consistency and inter-view style transfer using self-view and cross-view attention mechanisms, respectively. By eliminating the need for model retraining and multi-view editing, our approach significantly reduces editing time and memory resource requirements, achieving runtimes approximately 20 times faster than SOTA methods. We have performed extensive experiments on various benchmark datasets, showcasing the diverse editing capabilities of our proposed technique.

Hasan Iqbal, Nazmul Karim, Umar Khalid et al.

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 years. To extend these capabilities to 4D scene, we introduce a progressive sampling framework for 4D editing (PSF-4D) that ensures temporal and multi-view consistency by intuitively controlling the noise initialization during forward diffusion. For temporal coherence, we design a correlated Gaussian noise structure that links frames over time, allowing each frame to depend meaningfully on prior frames. Additionally, to ensure spatial consistency across views, we implement a cross-view noise model, which uses shared and independent noise components to balance commonalities and distinct details among different views. To further enhance spatial coherence, PSF-4D incorporates view-consistent iterative refinement, embedding view-aware information into the denoising process to ensure aligned edits across frames and views. Our approach enables high-quality 4D editing without relying on external models, addressing key challenges in previous methods. Through extensive evaluation on multiple benchmarks and multiple editing aspects (e.g., style transfer, multi-attribute editing, object removal, local editing, etc.), we show the effectiveness of our proposed method. Experimental results demonstrate that our proposed method outperforms state-of-the-art 4D editing methods in diverse benchmarks.

Umar Khalid, Kashif Munir, Hasan Iqbal et al.

Editing complex visual content from ambiguous or partially specified instructions remains a core challenge in vision-language modeling. Existing models can contextualize content but often fail to infer the underlying intent within a reference image or scene, leading to inconsistent or misaligned edits. We introduce the Editing Vision-Language Model (EVLM), a system that interprets ambiguous instructions in conjunction with reference visuals to produce precise, context-aware editing prompts. EVLM's key innovation is a reflective reasoning framework that translates subjective user intent into structured, actionable outputs by aligning with human-rated rationales through Reflection-Aware KL-Divergence Target Optimization (RKTO). By combining Chain-of-Thought (CoT) reasoning with RKTO alignment, EVLM captures fine-grained editing preferences without relying on binary supervision. Trained on a dataset of 30,000 CoT examples with human-annotated rationale quality, EVLM achieves substantial gains in alignment with human intent. Experiments across image, video, 3D, and 4D editing tasks show that EVLM generates coherent and high-quality instructions, providing a scalable foundation for multimodal editing and reasoning.

Nazmul Karim, Umar Khalid, Mohsen Joneidi et al.

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 success by either training text-to-video (T2V) models on a very large number of text-video pairs or adapting T2I models on text-video pairs independently. Although the latter is computationally less expensive, it still takes a significant amount of time for per-video adaption. To address this issue, we propose SAVE, a novel spectral-shift-aware adaptation framework, in which we fine-tune the spectral shift of the parameter space instead of the parameters themselves. Specifically, we take the spectral decomposition of the pre-trained T2I weights and only update the singular values while freezing the corresponding singular vectors. In addition, we introduce a spectral shift regularizer aimed at placing tighter constraints on larger singular values compared to smaller ones. This form of regularization enables the model to grasp finer details within the video that align with the provided textual descriptions. We also offer theoretical justification for our proposed regularization technique. Since we are only dealing with spectral shifts, the proposed method reduces the adaptation time significantly (approx. 10 times) and has fewer resource constraints for training. Such attributes posit SAVE to be more suitable for real-world applications, e.g. editing undesirable content during video streaming. We validate the effectiveness of SAVE with an extensive experimental evaluation under different settings, e.g. style transfer, object replacement, privacy preservation, etc.

Nazmul Karim, Umar Khalid, Nick Meeker et al.

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-supervised approaches. In this work, we present an approach that combines Ad-versarial Pre-Training with Triplet Loss AdversarialFine-Tuning. We compare our methods with the pre-trained ResNet50 model that forms the backbone of FaceNet, finetuned on our CelebA dataset. 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. This seems promising, increasing the training time for fine-tuning should yield even better results. In addition to this, a modified semi-supervised experiment was conducted, which demonstrated the improvement of contrastive adversarial training with the introduction of small amounts of labels.

Ashkan Esmaeili, Mohsen Joneidi, Mehrdad Salimitari et al.

The problem of simultaneous column and row subset selection is addressed in this paper. The column space and row space of a matrix are spanned by its left and right singular vectors, respectively. However, the singular vectors are not within actual columns/rows of the matrix. In this paper, an iterative approach is proposed to capture the most structural information of columns/rows via selecting a subset of actual columns/rows. This algorithm is referred to as two-way spectrum pursuit (TWSP) which provides us with an accurate solution for the CUR matrix decomposition. TWSP is applicable in a wide range of applications since it enjoys a linear complexity w.r.t. number of original columns/rows. We demonstrated the application of TWSP for joint channel and sensor selection in cognitive radio networks, informative users and contents detection, and efficient supervised data reduction.