no code implementations • 18 Apr 2024 • Md Adnan Arefeen, Biplob Debnath, Md Yusuf Sarwar Uddin, Srimat Chakradhar
Use of RAG for combined understanding of multimodal data such as text, images and videos is appealing but two critical limitations exist: one-time, upfront capture of all content in large multimodal data as text descriptions entails high processing times, and not all information in the rich multimodal data is typically in the text descriptions.
no code implementations • 2 Sep 2023 • Md Adnan Arefeen, Biplob Debnath, Srimat Chakradhar
Additionally, if free pretrained LLM-based summarizers are used to reduce context (into human consumable summaries), LeanContext can further modify the reduced context to enhance the accuracy (ROUGE-1 score) by $13. 22\%$ to $24. 61\%$.
no code implementations • 13 May 2023 • Md Adnan Arefeen, Zhouyu Li, Md Yusuf Sarwar Uddin, Anupam Das
To achieve this, we propose a channel squeeze-excitation based feature metamorphosis module, Cross-SEC, to achieve distinct attention of all tasks and a de-correlation loss function with differential-privacy to train a deep learning model that produces distinct privacy-aware features as an output for the respective tasks.
no code implementations • 22 Mar 2022 • Md Adnan Arefeen, Sumaiya Tabassum Nimi, Md Yusuf Sarwar Uddin
Detection-driven real-time video analytics require continuous detection of objects contained in the video frames using deep learning models like YOLOV3, EfficientDet.
no code implementations • 25 Jun 2021 • Sumaiya Tabassum Nimi, Md Adnan Arefeen, Md Yusuf Sarwar Uddin, Yugyung Lee
Collaborative inference enables resource-constrained edge devices to make inferences by uploading inputs (e. g., images) to a server (i. e., cloud) where the heavy deep learning models run.
no code implementations • 15 Jun 2021 • Md Adnan Arefeen, Sumaiya Tabassum Nimi, Md Yusuf Sarwar Uddin, Zhu Li
In this paper, we propose a transfer-learning based model construction technique for the aerial scene classification problem.
Ranked #5 on Aerial Scene Classification on UCM (50% as trainset)