no code implementations • 24 Mar 2023 • Abbavaram Gowtham Reddy, Saketh Bachu, Harsharaj Pathak, Benin L Godfrey, Vineeth N. Balasubramanian, Varshaneya V, Satya Narayanan Kar
Recently, there has been a growing interest in learning and explaining causal effects within Neural Network (NN) models.
no code implementations • 17 Jan 2023 • Tarun Ram Menta, Surgan Jandial, Akash Patil, Vimal KB, Saketh Bachu, Balaji Krishnamurthy, Vineeth N. Balasubramanian, Chirag Agarwal, Mausoom Sarkar
As transfer learning techniques are increasingly used to transfer knowledge from the source model to the target task, it becomes important to quantify which source models are suitable for a given target task without performing computationally expensive fine tuning.
no code implementations • 8 May 2022 • Vedant Singh, Surgan Jandial, Ayush Chopra, Siddharth Ramesh, Balaji Krishnamurthy, Vineeth N. Balasubramanian
Conditional image generation has paved the way for several breakthroughs in image editing, generating stock photos and 3-D object generation.
1 code implementation • 10 Nov 2021 • Rahul Vigneswaran, Marc T. Law, Vineeth N. Balasubramanian, Makarand Tapaswi
Oversampling instances of the tail classes attempts to solve this imbalance.
Ranked #1 on Long-tail Learning on mini-ImageNet-LT
1 code implementation • NeurIPS 2020 • K J Joseph, Vineeth N. Balasubramanian
The ability to continuously learn and adapt itself to new tasks, without losing grasp of already acquired knowledge is a hallmark of biological learning systems, which current deep learning systems fall short of.
no code implementations • 28 Sep 2020 • Puneet Mangla, Nupur Kumari, Mayank Singh, Vineeth N. Balasubramanian, Balaji Krishnamurthy
Recent advances in generative adversarial networks (GANs) have shown remarkable progress in generating high-quality images.
1 code implementation • 17 Aug 2020 • Udit Maniyar, Joseph K J, Aniket Anand Deshmukh, Urun Dogan, Vineeth N. Balasubramanian
Domain generalization (DG) methods try to learn a model that when trained on data from multiple domains, would generalize to a new unseen domain.
no code implementations • 8 Aug 2020 • Sandeep Inuganti, Vineeth N. Balasubramanian
Most of these works have a pre-trained object detection model as a preliminary feature extractor.
no code implementations • 15 Jul 2020 • Shivam Chandhok, Vineeth N. Balasubramanian
The performance of generative zero-shot methods mainly depends on the quality of generated features and how well the model facilitates knowledge transfer between visual and semantic domains.
no code implementations • 18 Jun 2020 • Akshay L Chandra, Sai Vikas Desai, Wei Guo, Vineeth N. Balasubramanian
In light of growing challenges in agriculture with ever growing food demand across the world, efficient crop management techniques are necessary to increase crop yield.
no code implementations • 14 Jun 2020 • Puneet Mangla, Vedant Singh, Vineeth N. Balasubramanian
A Very recent trend has emerged to couple the notion of interpretability and adversarial robustness, unlike earlier efforts which solely focused on good interpretations or robustness against adversaries.
no code implementations • 30 Apr 2020 • Arghya Pal, Vineeth N. Balasubramanian
The paucity of large curated hand-labeled training data forms a major bottleneck in the deployment of machine learning models in computer vision and other fields.
no code implementations • 14 Mar 2020 • Puneet Mangla, Vedant Singh, Shreyas Jayant Havaldar, Vineeth N. Balasubramanian
The vicinal risk minimization (VRM) principle is an empirical risk minimization (ERM) variant that replaces Dirac masses with vicinal functions.
2 code implementations • 16 Jan 2020 • Harshitha Machiraju, Vineeth N. Balasubramanian
Small, carefully crafted perturbations called adversarial perturbations can easily fool neural networks.
1 code implementation • ECCV 2020 • Mayank Singh, Nupur Kumari, Puneet Mangla, Abhishek Sinha, Vineeth N. Balasubramanian, Balaji Krishnamurthy
Safe deployment of machine learning system mandates that the prediction and its explanation be reliable and robust.
Ranked #1 on Weakly-Supervised Object Localization on CUB-200-2011 (Top-1 Error Rate metric)
BIG-bench Machine Learning Weakly-Supervised Object Localization
no code implementations • 4 Oct 2019 • Akshay L Chandra, Sai Vikas Desai, Vineeth N. Balasubramanian, Seishi Ninomiya, Wei Guo
We show promising results on two publicly available cereal crop datasets - Sorghum and Wheat.
no code implementations • 7 Aug 2019 • Sai Vikas Desai, Akshay L Chandra, Wei Guo, Seishi Ninomiya, Vineeth N. Balasubramanian
Our extensive experiments show that the proposed framework can be used to train good generalizable models with much lesser annotation costs than the state of the art active learning approaches for object detection.
no code implementations • 2 Aug 2019 • Puneet Mangla, Surgan Jandial, Sakshi Varshney, Vineeth N. Balasubramanian
Adversarial examples are fabricated examples, indistinguishable from the original image that mislead neural networks and drastically lower their performance.
7 code implementations • 28 Jul 2019 • Puneet Mangla, Mayank Singh, Abhishek Sinha, Nupur Kumari, Vineeth N. Balasubramanian, Balaji Krishnamurthy
A recent regularization technique - Manifold Mixup focuses on learning a general-purpose representation, robust to small changes in the data distribution.
1 code implementation • 20 Jun 2019 • K J Joseph, Vamshi Teja R, Krishnakant Singh, Vineeth N. Balasubramanian
Mini-batch gradient descent based methods are the de facto algorithms for training neural network architectures today.
no code implementations • 19 Jun 2019 • Sai Vikas Desai, Vineeth N. Balasubramanian, Tokihiro Fukatsu, Seishi Ninomiya, Wei Guo
Accurate estimation of heading date of paddy rice greatly helps the breeders to understand the adaptability of different crop varieties in a given location.
1 code implementation • 21 May 2019 • Chaitanya Devaguptapu, Ninad Akolekar, Manuj M Sharma, Vineeth N. Balasubramanian
Can we improve detection in the thermal domain by borrowing features from rich domains like visual RGB?
1 code implementation • 13 May 2019 • Mayank Singh, Abhishek Sinha, Nupur Kumari, Harshitha Machiraju, Balaji Krishnamurthy, Vineeth N. Balasubramanian
We analyze the adversarially trained robust models to study their vulnerability against adversarial attacks at the level of the latent layers.
no code implementations • 7 Apr 2019 • Varshaneya V, S. Balasubramanian, Vineeth N. Balasubramanian
In this paper, we propose a standalone GAN architecture SkeGAN and a VAE-GAN architecture VASkeGAN, for sketch generation in vector format.
1 code implementation • CVPR 2019 • Arghya Pal, Vineeth N. Balasubramanian
Our proposed methodology out-performs state-of-the-art models (which use ground truth)on each of our zero-shot tasks, showing promise on zero-shot task transfer.
1 code implementation • 6 Feb 2019 • Aditya Chattopadhyay, Piyushi Manupriya, Anirban Sarkar, Vineeth N. Balasubramanian
We propose a new attribution method for neural networks developed using first principles of causality (to the best of our knowledge, the first such).
no code implementations • 1 Feb 2019 • Vaibhav B Sinha, Sneha Kudugunta, Adepu Ravi Sankar, Surya Teja Chavali, Purushottam Kar, Vineeth N. Balasubramanian
We present DANTE, a novel method for training neural networks using the alternating minimization principle.
1 code implementation • 9 Jan 2019 • Thrupthi Ann John, Isha Dua, Vineeth N. Balasubramanian, C. V. Jawahar
Do we know what the different filters of a face network represent?
1 code implementation • 20 Sep 2018 • K J Joseph, Vineeth N. Balasubramanian
This paper proposes a simple, yet very effective method to localize dominant foreground objects in an image, to pixel-level precision.
no code implementations • ECCV 2018 • Parikshit Sakurikar, Ishit Mehta, Vineeth N. Balasubramanian, P. J. Narayanan
Post-capture control of the focus position of an image is a useful photographic tool.
no code implementations • 21 Jul 2018 • Adepu Ravi Sankar, Vishwak Srinivasan, Vineeth N. Balasubramanian
Theoretical analysis of the error landscape of deep neural networks has garnered significant interest in recent years.
1 code implementation • CVPR 2018 • Arghya Pal, Vineeth N. Balasubramanian
In this work, we present Adversarial Data Programming (ADP), which presents an adversarial methodology to generate data as well as a curated aggregated label has given a set of weak labeling functions.
3 code implementations • 7 Mar 2018 • Vaibhav B Sinha, Sukrut Rao, Vineeth N. Balasubramanian
A well-known approach for aggregation is the Dawid-Skene (DS) algorithm, which is based on the principle of Expectation-Maximization (EM).
no code implementations • 20 Dec 2017 • Vishwak Srinivasan, Adepu Ravi Sankar, Vineeth N. Balasubramanian
Using this motivation, we propose our method $\textit{ADINE}$ that helps weigh the previous updates more (by setting the momentum parameter $> 1$), evaluate our proposed algorithm on deep neural networks and show that $\textit{ADINE}$ helps the learning algorithm to converge much faster without compromising on the generalization error.
1 code implementation • 11 Nov 2017 • Supriya Pandhre, Himangi Mittal, Manish Gupta, Vineeth N. Balasubramanian
In this paper, we present a novel approach, STWalk, for learning trajectory representations of nodes in temporal graphs.
22 code implementations • 30 Oct 2017 • Aditya Chattopadhyay, Anirban Sarkar, Prantik Howlader, Vineeth N. Balasubramanian
Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems.
1 code implementation • ICCV 2017 • Tanya Marwah, Gaurav Mittal, Vineeth N. Balasubramanian
This paper proposes a network architecture to perform variable length semantic video generation using captions.
no code implementations • 23 Jun 2017 • Hemanth Venkateswara, Vineeth N. Balasubramanian, Prasanth Lade, Sethuraman Panchanathan
The emergence of depth imaging technologies like the Microsoft Kinect has renewed interest in computational methods for gesture classification based on videos.
1 code implementation • 7 Jun 2017 • Adepu Ravi Sankar, Vineeth N. Balasubramanian
However, in this work, we propose a new hypothesis based on recent theoretical findings and empirical studies that deep neural network models actually converge to saddle points with high degeneracy.
2 code implementations • 30 Dec 2016 • Supriya Pandhre, Manish Gupta, Vineeth N. Balasubramanian
Although various kinds of outliers have been studied for graph data, there is not much work on anomaly detection from edge-attributed graphs.
Social and Information Networks G.2; G.3; H.2.8
1 code implementation • 30 Nov 2016 • Gaurav Mittal, Tanya Marwah, Vineeth N. Balasubramanian
This paper introduces a novel approach for generating videos called Synchronized Deep Recurrent Attentive Writer (Sync-DRAW).
no code implementations • 30 Oct 2016 • Bharat Bhusan Sau, Vineeth N. Balasubramanian
The remarkable successes of deep learning models across various applications have resulted in the design of deeper networks that can solve complex problems.