no code implementations • 23 Nov 2023 • Alif Elham Khan, Mohammad Junayed Hasan, Humayra Anjum, Nabeel Mohammed
Its effectiveness and robustness across balanced, imbalanced, medical, and non-medical image datasets suggests that it is not specific to a particular model or dataset but demonstrates superior performance consistently while using less memory and computation.
1 code implementation • 6 Nov 2023 • Sadia Afrin, Md. Shahad Mahmud Chowdhury, Md. Ekramul Islam, Faisal Ahamed Khan, Labib Imam Chowdhury, MD. Motahar Mahtab, Nazifa Nuha Chowdhury, Massud Forkan, Neelima Kundu, Hakim Arif, Mohammad Mamun Or Rashid, Mohammad Ruhul Amin, Nabeel Mohammed
Lemmatization holds significance in both natural language processing (NLP) and linguistics, as it effectively decreases data density and aids in comprehending contextual meaning.
1 code implementation • 18 Oct 2023 • Fahimul Hoque Shubho, Townim Faisal Chowdhury, Ali Cheraghian, Morteza Saberi, Nabeel Mohammed, Shafin Rahman
Then, we enrich word vectors by combining the word embeddings from class names and descriptions generated by ChatGPT.
1 code implementation • 5 Oct 2023 • Md. Ismail Hossain, M M Lutfe Elahi, Sameera Ramasinghe, Ali Cheraghian, Fuad Rahman, Nabeel Mohammed, Shafin Rahman
In knowledge distillation literature, feature-based methods have dominated due to their ability to effectively tap into extensive teacher models.
Ranked #1 on Classification on CIFAR-100
1 code implementation • 25 Jul 2023 • Mominul Islam, Hasib Zunair, Nabeel Mohammed
FBGT involves the removal of real images that exhibit similarities to images of other classes before utilizing them as the training dataset for a GAN.
no code implementations • 9 Jun 2023 • Md. Ekramul Islam, Labib Chowdhury, Faisal Ahamed Khan, Shazzad Hossain, Sourave Hossain, Mohammad Mamun Or Rashid, Nabeel Mohammed, Mohammad Ruhul Amin
This study introduces SentiGOLD, a Bangla multi-domain sentiment analysis dataset.
1 code implementation • 7 Apr 2023 • Shadman Rohan, Mojammel Hossain, Mohammad Mamun Or Rashid, Nabeel Mohammed
While widely studied for English and other resource-rich languages, research on coreference resolution in Bengali largely remains unexplored due to the absence of relevant datasets.
1 code implementation • 24 Dec 2022 • Md. Ismail Hossain, Mohammed Rakib, M. M. Lutfe Elahi, Nabeel Mohammed, Shafin Rahman
This research aims to generate winning lottery tickets from a set of lottery tickets that can achieve similar accuracy to the original unpruned network.
no code implementations • 24 Dec 2022 • Abu Adnan Sadi, Labib Chowdhury, Nursrat Jahan, Mohammad Newaz Sharif Rafi, Radeya Chowdhury, Faisal Ahamed Khan, Nabeel Mohammed
In this study, we propose a novel loss function to train neural network models to mitigate this critical issue in this important field.
1 code implementation • 14 Oct 2022 • Md. Shakib Khan, Kazi Nabiul Alam, Abdur Rab Dhruba, Hasib Zunair, Nabeel Mohammed
As well as with fewer learnable parameters, 0. 26 million (M) compared to 42. 5M using knowledge distillation with the goal to detect melanoma from dermoscopic images.
1 code implementation • 9 Oct 2022 • Md. Tahrim Faroque, Yan Yang, Md Zakir Hossain, Sheikh Motahar Naim, Nabeel Mohammed, Shafin Rahman
Smile veracity classification is a task of interpreting social interactions.
no code implementations • 13 Sep 2022 • Mohammed Rakib, Md. Ismail Hossain, Nabeel Mohammed, Fuad Rahman
Although over 300M around the world speak Bangla, scant work has been done in improving Bangla voice-to-text transcription due to Bangla being a low-resource language.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 23 May 2022 • Md Sazzad Hossain, Pritom Saha, Townim Faisal Chowdhury, Shafin Rahman, Fuad Rahman, Nabeel Mohammed
A common goal of task-incremental methods is to design a network that can operate on minimal size, maintaining decent performance.
1 code implementation • 23 May 2022 • Md. Ismail Hossain, Mohammed Rakib, Sabbir Mollah, Fuad Rahman, Nabeel Mohammed
Word-level handwritten optical character recognition (OCR) remains a challenge for morphologically rich languages like Bangla.
2 code implementations • 23 Apr 2022 • Md. Istiak Hossain Shihab, Nazia Tasnim, Hasib Zunair, Labiba Kanij Rupty, Nabeel Mohammed
Multi-class product counting and recognition identifies product items from images or videos for automated retail checkout.
1 code implementation • 27 Jan 2022 • Fahad Rahman Amik, Ahnaf Ismat Tasin, Silvia Ahmed, M. M. Lutfe Elahi, Nabeel Mohammed
This approach of distilling knowledge has gained popularity as a result of the prohibitively complicated nature of such cumbersome models for deployment on edge computing devices.
1 code implementation • 21 Aug 2021 • Labib Chowdhury, Mustafa Kamal, Najia Hasan, Nabeel Mohammed
The advantage of such a curriculum learning-based techniques is that it will impose inter-class margins as well as taking to account easy and hard samples.
1 code implementation • 26 May 2021 • Hasib Zunair, Aimon Rahman, Nabeel Mohammed
We explore the idea of whether pretraining a model on realistic videos could improve performance rather than training the model from scratch, intended for tuberculosis type classification from chest CT scans.
1 code implementation • 15 Apr 2021 • Koushik Roy, Md. Hasan, Labiba Rupty, Md. Sourave Hossain, Shirshajit Sengupta, Shehzad Noor Taus, Nabeel Mohammed
The emergence of biometric-based authentication using modern sensors on electronic devices has led to an escalated use of face recognition technologies.
Ranked #1 on Face Anti-Spoofing on OULU-NPU
no code implementations • 1 Mar 2021 • Md. Sourave Hossain, Labiba Rupty, Koushik Roy, Md. Hasan, Shirshajit Sengupta, Nabeel Mohammed
Face Anti Spoofing (FAS) systems are used to identify malicious spoofing attempts targeting face recognition systems using mediums such as video replay or printed papers.
Ranked #3 on Face Anti-Spoofing on OULU-NPU
3 code implementations • 26 Jul 2020 • Hasib Zunair, Aimon Rahman, Nabeel Mohammed, Joseph Paul Cohen
A common approach to medical image analysis on volumetric data uses deep 2D convolutional neural networks (CNNs).
no code implementations • 2 Sep 2018 • Motiur Rahman, Nabeel Mohammed, Nafees Mansoor, Sifat Momen
The results show that the model has successfully been able to learn a working language model and to generate captions of images quite accurately in many cases.
no code implementations • 22 Feb 2017 • Mithun Biswas, Rafiqul Islam, Gautam Kumar Shom, Md. Shopon, Nabeel Mohammed, Sifat Momen, Md Anowarul Abedin
Bangla handwriting recognition is becoming a very important issue nowadays.