no code implementations • 11 Dec 2023 • Sahil Khose, Anisha Pal, Aayushi Agarwal, Deepanshi, Judy Hoffman, Prithvijit Chattopadhyay
Real-world aerial scene understanding is limited by a lack of datasets that contain densely annotated images curated under a diverse set of conditions.
1 code implementation • 28 Aug 2023 • Ran Liu, Sahil Khose, Jingyun Xiao, Lakshmi Sathidevi, Keerthan Ramnath, Zsolt Kira, Eva L. Dyer
To address this challenge, we propose a novel approach for distribution-aware latent augmentation that leverages the relationships across samples to guide the augmentation procedure.
1 code implementation • 21 Sep 2022 • Aditya Kane, V Manushree, Sahil Khose
Thus, we instead use pre-trained embeddings of text and image from this model for our supervised training and surpass previous state-of-the-art results on the FloodNet dataset.
1 code implementation • 30 May 2022 • Aditya Kane, Sahil Khose
Designing efficient and reliable VQA systems remains a challenging problem, more so in the case of disaster management and response systems.
no code implementations • WASSA (ACL) 2022 • Aditya Kane, Shantanu Patankar, Sahil Khose, Neeraja Kirtane
Detecting emotions in languages is important to accomplish a complete interaction between humans and machines.
1 code implementation • NeurIPS Workshop ICBINB 2021 • Sahil Khose, Shruti Jain, V Manushree
This paper is an ablation study of distillation in a semi-supervised setting, which not just reduces the number of parameters of the model but can achieve this while improving the performance over the baseline supervised model and making it better at generalizing.
2 code implementations • 26 Aug 2021 • V Manushree, Sameer Saxena, Parna Chowdhury, Manisimha Varma, Harsh Rathod, Ankita Ghosh, Sahil Khose
Sketches are a medium to convey a visual scene from an individual's creative perspective.
2 code implementations • 16 May 2021 • Sahil Khose, Abhiraj Tiwari, Ankita Ghosh
FloodNet is a high-resolution image dataset acquired by a small UAV platform, DJI Mavic Pro quadcopters, after Hurricane Harvey.
1 code implementation • NAACL (SMM4H) 2021 • Sidharth R, Abhiraj Tiwari, Parthivi Choubey, Saisha Kashyap, Sahil Khose, Kumud Lakara, Nishesh Singh, Ujjwal Verma
This paper describes our submissions for the Social Media Mining for Health (SMM4H)2021 shared tasks.