1 citations · 1 across the 11 of their papers we have counts for
12 papers
Finetune-Informed Pretraining Boosts Downstream Performance
Atik Faysal, Mohammad Rostami, Reihaneh Gh. Roshan +2
Multimodal pretraining is effective for building general-purpose representations, but in many practical deployments, only one modality is heavily used during downstream fine-tuning…
Semi-Supervised Masked Autoencoders: Unlocking Vision Transformer Potential with Limited Data
Atik Faysal, Mohammad Rostami, Reihaneh Gh. Roshan +2
We address the challenge of training Vision Transformers (ViTs) when labeled data is scarce but unlabeled data is abundant. We propose Semi-Supervised Masked Autoencoder (SSMAE), a…
CageDroneRF: A Large-Scale RF Benchmark and Toolkit for Drone Perception
Mohammad Rostami, Atik Faysal, Hongtao Xia +3
We present CageDroneRF (CDRF), a large-scale benchmark for Radio-Frequency (RF) drone detection and identification built from real-world captures and systematically generated synth…
Large Language Models Can Perform Automatic Modulation Classification via Discretized Self-supervised Candidate Retrieval
Mohammad Rostami, Atik Faysal, Reihaneh Gh. Roshan +3
Identifying wireless modulation schemes is essential for cognitive radio, but standard supervised models often degrade under distribution shift, and training domain-specific wirele…
Privacy Preserving Semantic Communications Using Vision Language Models: A Segmentation and Generation Approach
Haoran Chang, Mingzhe Chen, Huaxia Wang +1
Semantic communication has emerged as a promising paradigm for next-generation wireless systems, improving the communication efficiency by transmitting high-level semantic features…
Plug-and-Play AMC: Context Is King in Training-Free, Open-Set Modulation with LLMs
Mohammad Rostami, Atik Faysal, Reihaneh Gh. Roshan +3
Automatic Modulation Classification (AMC) is critical for efficient spectrum management and robust wireless communications. However, AMC remains challenging due to the complex inte…
DenoMAE2.0: Improving Denoising Masked Autoencoders by Classifying Local Patches
Atik Faysal, Mohammad Rostami, Taha Boushine +3
We introduce DenoMAE2.0, an enhanced denoising masked autoencoder that integrates a local patch classification objective alongside traditional reconstruction loss to improve repres…
DenoMAE: A Multimodal Autoencoder for Denoising Modulation Signals
Atik Faysal, Taha Boushine, Mohammad Rostami +5
We propose Denoising Masked Autoencoder (Deno-MAE), a novel multimodal autoencoder framework for denoising modulation signals during pretraining. DenoMAE extends the concept of mas…
NMformer: A Transformer for Noisy Modulation Classification in Wireless Communication
Atik Faysal, Mohammad Rostami, Reihaneh Gh. Roshan +2
Modulation classification is a very challenging task since the signals intertwine with various ambient noises. Methods are required that can classify them without adding extra step…
SimO Loss: Anchor-Free Contrastive Loss for Fine-Grained Supervised Contrastive Learning
Taha Bouhsine, Imad El Aaroussi, Atik Faysal +1
We introduce a novel anchor-free contrastive learning (AFCL) method leveraging our proposed Similarity-Orthogonality (SimO) loss. Our approach minimizes a semi-metric discriminativ…
Meta-Task: A Method-Agnostic Framework for Learning to Regularize in Few-Shot Learning
Mohammad Rostami, Atik Faysal, Huaxia Wang +1
Overfitting is a significant challenge in Few-Shot Learning (FSL), where models trained on small, variable datasets tend to memorize rather than generalize to unseen tasks. Regular…
Unsupervised Representation Learning to Aid Semi-Supervised Meta Learning
Atik Faysal, Mohammad Rostami, Huaxia Wang +2
Few-shot learning or meta-learning leverages the data scarcity problem in machine learning. Traditionally, training data requires a multitude of samples and labeling for supervised…