no code implementations • 10 Dec 2023 • Angel Daruna, Yunye Gong, Abhinav Rajvanshi, Han-Pang Chiu, Yi Yao
Our implementation balances the benefits of sampling and analytical propagation techniques, which we believe, is a key factor in achieving performance improvements.
no code implementations • 25 Oct 2023 • Xingchen Zhao, Niluthpol Chowdhury Mithun, Abhinav Rajvanshi, Han-Pang Chiu, Supun Samarasekera
Recent state-of-the-art (SOTA) UDA methods employ a teacher-student self-training approach, where a teacher model is used to generate pseudo-labels for the new data which in turn guide the training process of the student model.
no code implementations • 8 Sep 2023 • Abhinav Rajvanshi, Karan Sikka, Xiao Lin, Bhoram Lee, Han-Pang Chiu, Alvaro Velasquez
We evaluate SayNav on multi-object navigation (MultiON) task, that requires the agent to utilize a massive amount of human knowledge to efficiently search multiple different objects in an unknown environment.
no code implementations • CVPR 2023 • Nazmul Karim, Niluthpol Chowdhury Mithun, Abhinav Rajvanshi, Han-Pang Chiu, Supun Samarasekera, Nazanin Rahnavard
In this regard, source-free domain adaptation (SFDA) excels as access to source data is no longer required during adaptation.
Ranked #4 on Source-Free Domain Adaptation on VisDA-2017
no code implementations • 28 Mar 2023 • Niluthpol Chowdhury Mithun, Kshitij Minhas, Han-Pang Chiu, Taragay Oskiper, Mikhail Sizintsev, Supun Samarasekera, Rakesh Kumar
Precise estimation of global orientation and location is critical to ensure a compelling outdoor Augmented Reality (AR) experience.
no code implementations • 19 May 2022 • James Seale Smith, Zachary Seymour, Han-Pang Chiu
As progress is made on training machine learning models on incrementally expanding classification tasks (i. e., incremental learning), a next step is to translate this progress to industry expectations.
no code implementations • 17 May 2022 • Zachary Seymour, Niluthpol Chowdhury Mithun, Han-Pang Chiu, Supun Samarasekera, Rakesh Kumar
Understanding the geometric relationships between objects in a scene is a core capability in enabling both humans and autonomous agents to navigate in new environments.
1 code implementation • 26 Aug 2021 • Muhammad Zubair Irshad, Niluthpol Chowdhury Mithun, Zachary Seymour, Han-Pang Chiu, Supun Samarasekera, Rakesh Kumar
This paper presents a novel approach for the Vision-and-Language Navigation (VLN) task in continuous 3D environments, which requires an autonomous agent to follow natural language instructions in unseen environments.
1 code implementation • 28 Jun 2021 • Junjiao Tian, Niluthpol Mithun, Zach Seymour, Han-Pang Chiu, Zsolt Kira
There are two major drawbacks to these methods: 1) constantly up-weighting minority classes can introduce excessive false positives in semantic segmentation; 2) a minority class is not necessarily a hard class.
no code implementations • 21 Mar 2021 • Zachary Seymour, Kowshik Thopalli, Niluthpol Mithun, Han-Pang Chiu, Supun Samarasekera, Rakesh Kumar
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics.
1 code implementation • 1 Jan 2021 • Junjiao Tian, Niluthpol Chowdhury Mithun, Zachary Seymour, Han-Pang Chiu, Zsolt Kira
Many works have proposed to weigh the standard cross entropy loss function with pre-computed weights based on class statistics such as the number of samples and class margins.
1 code implementation • 12 Sep 2020 • Niluthpol Chowdhury Mithun, Karan Sikka, Han-Pang Chiu, Supun Samarasekera, Rakesh Kumar
To enable large-scale evaluation, we introduce a new dataset containing over 550K pairs (covering 143 km^2 area) of RGB and aerial LIDAR depth images.
no code implementations • 8 Dec 2018 • Zachary Seymour, Karan Sikka, Han-Pang Chiu, Supun Samarasekera, Rakesh Kumar
Furthermore, we present an extensive study demonstrating the contribution of each component of our model, showing $8$--$15\%$ and $4\%$ improvement from adding semantic information and our proposed attention module.
no code implementations • 2 Jan 2018 • Varun Murali, Han-Pang Chiu, Supun Samarasekera, Rakesh, Kumar
Experimental evaluations validate that the injection of semantic information associated with visual landmarks using our approach achieves substantial improvements in accuracy on GPS-denied navigation solutions for large-scale urban scenarios