5 papers
Personalized Federated Segmentation with Shared Feature Aggregation and Boundary-Focused Calibration
Ishmam Tashdeed, Md. Atiqur Rahman, Sabrina Islam +1
Personalized federated learning (PFL) possesses the unique capability of preserving data confidentiality among clients while tackling the data heterogeneity problem of non-independ…
BdSL-SPOTER: A Transformer-Based Framework for Bengali Sign Language Recognition with Cultural Adaptation
Sayad Ibna Azad, Md. Atiqur Rahman
We introduce BdSL-SPOTER, a pose-based transformer framework for accurate and efficient recognition of Bengali Sign Language (BdSL). BdSL-SPOTER extends the SPOTER paradigm with cu…
Challenges and Solutions in Selecting Optimal Lossless Data Compression Algorithms
Md. Atiqur Rahman, MM Fazle Rabbi
The rapid growth of digital data has heightened the demand for efficient lossless compression methods. However, existing algorithms exhibit trade-offs: some achieve high compressio…
LLM-Based Evaluation of Low-Resource Machine Translation: A Reference-less Dialect Guided Approach with a Refined Sylheti-English Benchmark
Md. Atiqur Rahman, Sabrina Islam, Mushfiqul Haque Omi
Evaluating machine translation (MT) for low-resource languages poses a persistent challenge, primarily due to the limited availability of high quality reference translations. This…
Evaluating the Reliability of CNN Models on Classifying Traffic and Road Signs using LIME
Md. Atiqur Rahman, Ahmed Saad Tanim, Sanjid Islam +3
The objective of this investigation is to evaluate and contrast the effectiveness of four state-of-the-art pre-trained models, ResNet-34, VGG-19, DenseNet-121, and Inception V3, in…