Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Vineeth N Balasubramanian

Vineeth N Balasubramanian

Canonical Saliency Maps: Decoding Deep Face Models


May 04, 2021
Thrupthi Ann John, Vineeth N Balasubramanian, C V Jawahar

* Under review 

  Access Paper or Ask Questions

Improving Attribution Methods by Learning Submodular Functions


Apr 27, 2021
Piyushi Manupriya, Saketha Nath Jagarlapudi, Tarun Ram Menta, Vineeth N Balasubramanian


  Access Paper or Ask Questions

Instance-wise Causal Feature Selection for Model Interpretation


Apr 26, 2021
Pranoy Panda, Sai Srinivas Kancheti, Vineeth N Balasubramanian

* 6 pages, 5 figures. Accepted at the Causality in Vision workshop, CVPR 2021 

  Access Paper or Ask Questions

Towards Open World Object Detection


Mar 03, 2021
K J Joseph, Salman Khan, Fahad Shahbaz Khan, Vineeth N Balasubramanian

* To appear in CVPR 2021 as an ORAL paper. Code is available in https://github.com/JosephKJ/OWOD 

  Access Paper or Ask Questions

Enhanced Regularizers for Attributional Robustness


Dec 28, 2020
Anindya Sarkar, Anirban Sarkar, Vineeth N Balasubramanian

* 15 pages, 18 figures, Accepted at AAAI 2021 

  Access Paper or Ask Questions

Data Instance Prior for Transfer Learning in GANs


Dec 08, 2020
Puneet Mangla, Nupur Kumari, Mayank Singh, Vineeth N Balasubramanian, Balaji Krishnamurthy


  Access Paper or Ask Questions

A Deeper Look at the Hessian Eigenspectrum of Deep Neural Networks and its Applications to Regularization


Dec 08, 2020
Adepu Ravi Sankar, Yash Khasbage, Rahul Vigneswaran, Vineeth N Balasubramanian

* Accepted at AAAI 2021 

  Access Paper or Ask Questions

On Initial Pools for Deep Active Learning


Nov 30, 2020
Akshay L Chandra, Sai Vikas Desai, Chaitanya Devaguptapu, Vineeth N Balasubramanian

* Accepted at Pre-registration Workshop NeurIPS (2020) - http://preregister.science/ 

  Access Paper or Ask Questions

Beyond VQA: Generating Multi-word Answer and Rationale to Visual Questions


Oct 24, 2020
Radhika Dua, Sai Srinivas Kancheti, Vineeth N Balasubramanian


  Access Paper or Ask Questions

Meta-Consolidation for Continual Learning


Oct 01, 2020
K J Joseph, Vineeth N Balasubramanian

* Accepted to NeurIPS 2020 

  Access Paper or Ask Questions

Zero Shot Domain Generalization


Aug 17, 2020
Udit Maniyar, Joseph K J, Aniket Anand Deshmukh, Urun Dogan, Vineeth N Balasubramanian

* Accepted to BMVC 2020 

  Access Paper or Ask Questions

Assisting Scene Graph Generation with Self-Supervision


Aug 08, 2020
Sandeep Inuganti, Vineeth N Balasubramanian


  Access Paper or Ask Questions

An Empirical Study on the Robustness of NAS based Architectures


Jul 16, 2020
Chaitanya Devaguptapu, Devansh Agarwal, Gaurav Mittal, Vineeth N Balasubramanian


  Access Paper or Ask Questions

Enhancing Generalized Zero-Shot Learning via Adversarial Visual-Semantic Interaction


Jul 15, 2020
Shivam Chandhok, Vineeth N Balasubramanian

* Under Submission 

  Access Paper or Ask Questions

On Saliency Maps and Adversarial Robustness


Jul 13, 2020
Puneet Mangla, Vedant Singh, Vineeth N Balasubramanian

* Accepted at ECML-PKDD 2020, Acknowledgements added 

  Access Paper or Ask Questions

Computer Vision with Deep Learning for Plant Phenotyping in Agriculture: A Survey


Jun 18, 2020
Akshay L Chandra, Sai Vikas Desai, Wei Guo, Vineeth N Balasubramanian

* Featured as an article at Journal of Advanced Computing and Communications, April 2020. arXiv admin note: text overlap with arXiv:1805.00881 by other authors 

  Access Paper or Ask Questions

Generative Adversarial Data Programming


Apr 30, 2020
Arghya Pal, Vineeth N Balasubramanian

* arXiv admin note: text overlap with arXiv:1803.05137 

  Access Paper or Ask Questions

VarMixup: Exploiting the Latent Space for Robust Training and Inference


Mar 14, 2020
Puneet Mangla, Vedant Singh, Shreyas Jayant Havaldar, Vineeth N Balasubramanian

* 21 pages, 7 figures, 5 Tables 

  Access Paper or Ask Questions

A Little Fog for a Large Turn


Jan 16, 2020
Harshitha Machiraju, Vineeth N Balasubramanian

* Accepted to WACV 2020 

  Access Paper or Ask Questions

On the Benefits of Attributional Robustness


Dec 10, 2019
Mayank Singh, Nupur Kumari, Puneet Mangla, Abhishek Sinha, Vineeth N Balasubramanian, Balaji Krishnamurthy


  Access Paper or Ask Questions

Active Learning with Weak Supervision for Cost-Effective Panicle Detection in Cereal Crops


Oct 15, 2019
Akshay L Chandra, Sai Vikas Desai, Vineeth N Balasubramanian, Seishi Ninomiya, Wei Guo

* Preprint. Under review as a journal paper at BMC Plant Methods 

  Access Paper or Ask Questions

Charting the Right Manifold: Manifold Mixup for Few-shot Learning


Aug 07, 2019
Puneet Mangla, Mayank Singh, Abhishek Sinha, Nupur Kumari, Vineeth N Balasubramanian, Balaji Krishnamurthy


  Access Paper or Ask Questions

An Adaptive Supervision Framework for Active Learning in Object Detection


Aug 07, 2019
Sai Vikas Desai, Akshay Chandra Lagandula, Wei Guo, Seishi Ninomiya, Vineeth N Balasubramanian

* Accepted in BMVC 2019 

  Access Paper or Ask Questions

AdvGAN++ : Harnessing latent layers for adversary generation


Aug 02, 2019
Puneet Mangla, Surgan Jandial, Sakshi Varshney, Vineeth N Balasubramanian

* 4 pages [Short paper] 

  Access Paper or Ask Questions