no code implementations • 5 Mar 2023 • Varun Gupta, Anbumani Subramanian, C. V. Jawahar, Rohit Saluja
MTSVD is challenging compared to the previous works in two aspects i) The traffic signs are generally not present in the vicinity of their cues, ii) The traffic signs cues are diverse and unique.
no code implementations • 23 Oct 2022 • Shubham Dokania, A. H. Abdul Hafez, Anbumani Subramanian, Manmohan Chandraker, C. V. Jawahar
Autonomous driving and assistance systems rely on annotated data from traffic and road scenarios to model and learn the various object relations in complex real-world scenarios.
1 code implementation • 16 Aug 2022 • Shubham Dokania, Anbumani Subramanian, Manmohan Chandraker, C. V. Jawahar
We show that using annotations and visual cues from existing datasets, we can facilitate automated multi-modal data generation, mimicking real scene properties with high-fidelity, along with mechanisms to diversify samples in a physically meaningful way.
1 code implementation • 18 Apr 2022 • Aman Goyal, Dev Agarwal, Anbumani Subramanian, C. V. Jawahar, Ravi Kiran Sarvadevabhatla, Rohit Saluja
In many Asian countries with unconstrained road traffic conditions, driving violations such as not wearing helmets and triple-riding are a significant source of fatalities involving motorcycles.
1 code implementation • 17 Jan 2022 • Arpit Bahety, Rohit Saluja, Ravi Kiran Sarvadevabhatla, Anbumani Subramanian, C. V. Jawahar
We obtain TCDCA of 96. 77% on the test videos, with a remarkable improvement of 22. 58% over baseline, and demonstrate that our counting module's performance is close to human level.
1 code implementation • WACV 2022 • Vaishnavi Khindkar, Chetan Arora, Vineeth N Balasubramanian, Anbumani Subramanian, C. V. Jawahar
Qualitative results demonstrate the ability of ILLUME to attend important object instances required for alignment.
no code implementations • 12 Nov 2021 • Ashutosh Agarwal, Anay Majee, Anbumani Subramanian, Chetan Arora
To overcome these pitfalls in metric learning based FSOD techniques, we introduce Attention Guided Cosine Margin (AGCM) that facilitates the creation of tighter and well separated class-specific feature clusters in the classification head of the object detector.
no code implementations • 28 Oct 2021 • Anay Majee, Anbumani Subramanian, Kshitij Agrawal
Our method outperforms State-of-the-Art (SoTA) approaches in FSOD on the India Driving Dataset (IDD) by upto 11 mAP points while suffering from the least class confusion of 20% given only 10 examples of each novel road object.
1 code implementation • 23 Oct 2021 • Prachi Garg, Rohit Saluja, Vineeth N Balasubramanian, Chetan Arora, Anbumani Subramanian, C. V. Jawahar
Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model.
no code implementations • 18 Aug 2021 • Anuj Tambwekar, Kshitij Agrawal, Anay Majee, Anbumani Subramanian
Incremental few-shot learning has emerged as a new and challenging area in deep learning, whose objective is to train deep learning models using very few samples of new class data, and none of the old class data.
no code implementations • 29 Jan 2021 • Anay Majee, Kshitij Agrawal, Anbumani Subramanian
Few-shot learning is a problem of high interest in the evolution of deep learning.
no code implementations • 10 Aug 2020 • Ameet Annasaheb Rahane, Anbumani Subramanian
Large scale image datasets are a growing trend in the field of machine learning.
no code implementations • 30 Sep 2019 • Kshitij Agrawal, Anbumani Subramanian
Autonomous driving relies on deriving understanding of objects and scenes through images.
2 code implementations • 26 Nov 2018 • Girish Varma, Anbumani Subramanian, Anoop Namboodiri, Manmohan Chandraker, C. V. Jawahar
It also reflects label distributions of road scenes significantly different from existing datasets, with most classes displaying greater within-class diversity.
no code implementations • 1 Oct 2018 • Adithya Subramanian, Anbumani Subramanian
Our approach also proposes a new method of using object detectors making it suitable for data annotation task.
1 code implementation • 30 Aug 2018 • Ashish Mehta, Adithya Subramanian, Anbumani Subramanian
We run our experiments to validate the MT-LfD framework in CARLA, an open-source urban driving simulator.