no code implementations • 28 Feb 2024 • Rishubh Parihar, Abhijnya Bhat, Saswat Mallick, Abhipsa Basu, Jogendra Nath Kundu, R. Venkatesh Babu
We train Attribute Distribution Predictor (ADP) - a small mlp that maps the latent features to the distribution of attributes.
no code implementations • 27 Nov 2023 • Sunandini Sanyal, Ashish Ramayee Asokan, Suvaansh Bhambri, Pradyumna YM, Akshay Kulkarni, Jogendra Nath Kundu, R Venkatesh Babu
Conventional domain adaptation algorithms aim to achieve better generalization by aligning only the task-discriminative causal factors between a source and target domain.
no code implementations • ICCV 2023 • Sunandini Sanyal, Ashish Ramayee Asokan, Suvaansh Bhambri, Akshay Kulkarni, Jogendra Nath Kundu, R. Venkatesh Babu
We are the first to utilize vision transformers for domain adaptation in a privacy-oriented source-free setting, and our approach achieves state-of-the-art performance on single-source, multi-source, and multi-target benchmarks
no code implementations • 28 Oct 2022 • Jogendra Nath Kundu, Suvaansh Bhambri, Akshay Kulkarni, Hiran Sarkar, Varun Jampani, R. Venkatesh Babu
Universal Domain Adaptation (UniDA) deals with the problem of knowledge transfer between two datasets with domain-shift as well as category-shift.
3 code implementations • 27 Jul 2022 • Jogendra Nath Kundu, Suvaansh Bhambri, Akshay Kulkarni, Hiran Sarkar, Varun Jampani, R. Venkatesh Babu
The prime challenge in unsupervised domain adaptation (DA) is to mitigate the domain shift between the source and target domains.
Source-Free Domain Adaptation Unsupervised Domain Adaptation
1 code implementation • 16 Jun 2022 • Jogendra Nath Kundu, Akshay Kulkarni, Suvaansh Bhambri, Deepesh Mehta, Shreyas Kulkarni, Varun Jampani, R. Venkatesh Babu
Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discriminability knowledge gathered from the labeled source data.
no code implementations • NeurIPS 2021 • Jogendra Nath Kundu, Siddharth Seth, Anirudh Jamkhandi, Pradyumna YM, Varun Jampani, Anirban Chakraborty, R. Venkatesh Babu
To this end, we cast 3D pose learning as a self-supervised adaptation problem that aims to transfer the task knowledge from a labeled source domain to a completely unpaired target.
Ranked #5 on Unsupervised 3D Human Pose Estimation on Human3.6M
no code implementations • NeurIPS 2021 • Mugalodi Rakesh, Jogendra Nath Kundu, Varun Jampani, R. Venkatesh Babu
Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques.
no code implementations • CVPR 2022 • Jogendra Nath Kundu, Siddharth Seth, Pradyumna YM, Varun Jampani, Anirban Chakraborty, R. Venkatesh Babu
The advances in monocular 3D human pose estimation are dominated by supervised techniques that require large-scale 2D/3D pose annotations.
Ranked #8 on Unsupervised 3D Human Pose Estimation on Human3.6M
Monocular 3D Human Pose Estimation Unsupervised 3D Human Pose Estimation +2
no code implementations • 9 Feb 2022 • Jogendra Nath Kundu, Akshay Kulkarni, Suvaansh Bhambri, Varun Jampani, R. Venkatesh Babu
However, we find that latent features derived from the Fourier-based amplitude spectrum of deep CNN features hold a more tractable mapping with domain discrimination.
1 code implementation • ICCV 2021 • Jogendra Nath Kundu, Akshay Kulkarni, Amit Singh, Varun Jampani, R. Venkatesh Babu
Unsupervised domain adaptation (DA) has gained substantial interest in semantic segmentation.
Ranked #4 on Domain Generalization on GTA5-to-Cityscapes
no code implementations • NeurIPS 2020 • Naveen Venkat, Jogendra Nath Kundu, Durgesh Kumar Singh, Ambareesh Revanur, R. Venkatesh Babu
Thus, we aim to utilize implicit alignment without additional training objectives to perform adaptation.
Domain Adaptation Multi-Source Unsupervised Domain Adaptation
no code implementations • ECCV 2020 • Jogendra Nath Kundu, Mugalodi Rakesh, Varun Jampani, Rahul Mysore Venkatesh, R. Venkatesh Babu
We present a self-supervised human mesh recovery framework to infer human pose and shape from monocular images in the absence of any paired supervision.
1 code implementation • ECCV 2020 • Jogendra Nath Kundu, Ambareesh Revanur, Govind Vitthal Waghmare, Rahul Mysore Venkatesh, R. Venkatesh Babu
Our approach not only generalizes to in-the-wild images, but also yields a superior trade-off between speed and performance, compared to prior top-down approaches.
no code implementations • ECCV 2020 • Jogendra Nath Kundu, Rahul Mysore Venkatesh, Naveen Venkat, Ambareesh Revanur, R. Venkatesh Babu
We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA).
no code implementations • 24 Jun 2020 • Jogendra Nath Kundu, Siddharth Seth, Rahul M. V, Mugalodi Rakesh, R. Venkatesh Babu, Anirban Chakraborty
However, generalizability of human pose estimation models developed using supervision on large-scale in-studio datasets remains questionable, as these models often perform unsatisfactorily on unseen in-the-wild environments.
no code implementations • IEEE Winter Conference on Applications of Computer Vision (WACV) 2020 • Jogendra Nath Kundu, Himanshu Buckchash, Priyanka Mandikal, Anirudh Jamkhandi, Venkatesh Babu Radhakrishnan
Modeling dynamics of human motion is one of the most challenging sequence modeling problem, with diverse applications in animation industry, human-robot interaction, motion-based surveillance, etc.
1 code implementation • CVPR 2020 • Jogendra Nath Kundu, Naveen Venkat, Rahul M. V, R. Venkatesh Babu
1) In the Procurement stage, we aim to equip the model for future source-free deployment, assuming no prior knowledge of the upcoming category-gap and domain-shift.
1 code implementation • CVPR 2020 • Jogendra Nath Kundu, Naveen Venkat, Ambareesh Revanur, Rahul M. V, R. Venkatesh Babu
Addressing this, we introduce a practical DA paradigm where a source-trained model is used to facilitate adaptation in the absence of the source dataset in future.
no code implementations • CVPR 2020 • Jogendra Nath Kundu, Siddharth Seth, Varun Jampani, Mugalodi Rakesh, R. Venkatesh Babu, Anirban Chakraborty
Camera captured human pose is an outcome of several sources of variation.
2 code implementations • ICCV 2019 • Jogendra Nath Kundu, Maharshi Gor, Dakshit Agrawal, R. Venkatesh Babu
Despite the remarkable success of generative adversarial networks, their performance seems less impressive for diverse training sets, requiring learning of discontinuous mapping functions.
1 code implementation • ICCV 2019 • Jogendra Nath Kundu, Nishank Lakkakula, R. Venkatesh Babu
In this paper, we propose UM-Adapt - a unified framework to effectively perform unsupervised domain adaptation for spatially-structured prediction tasks, simultaneously maintaining a balanced performance across individual tasks in a multi-task setting.
3 code implementations • 6 Dec 2018 • Jogendra Nath Kundu, Maharshi Gor, Phani Krishna Uppala, R. Venkatesh Babu
In this work we propose a novel temporal pose-sequence modeling framework, which can embed the dynamics of 3D human-skeleton joints to a continuous latent space in an efficient manner.
3 code implementations • 6 Dec 2018 • Jogendra Nath Kundu, Maharshi Gor, R. Venkatesh Babu
The discriminator is trained also to regress this extrinsic factor r, which is used alongside with the intrinsic factor (encoded starting pose sequence) to generate a particular pose sequence.
2 code implementations • 3 Sep 2018 • Jogendra Nath Kundu, Rahul M. V., Aditya Ganeshan, R. Venkatesh Babu
In this work, we propose a data-efficient method which utilizes the geometric regularity of intraclass objects for pose estimation.
2 code implementations • 3 Aug 2018 • Jogendra Nath Kundu, Aditya Ganeshan, Rahul M. V., Aditya Prakash, R. Venkatesh Babu
Such image comparison based approach also alleviates the problem of data scarcity and hence enhances scalability of the proposed approach for novel object categories with minimal annotation.
no code implementations • CVPR 2018 • Jogendra Nath Kundu, Phani Krishna Uppala, Anuj Pahuja, R. Venkatesh Babu
Supervised deep learning methods have shown promising results for the task of monocular depth estimation; but acquiring ground truth is costly, and prone to noise as well as inaccuracies.