172 citations · 1.2k across the 80 of their papers we have counts for
19 papers · 1 filter
Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data
Harsh Rangwani, Sumukh K Aithal, Mayank Mishra +1
Real-world datasets exhibit imbalances of varying types and degrees. Several techniques based on re-weighting and margin adjustment of loss are often used to enhance the performanc…
Subsidiary Prototype Alignment for Universal Domain Adaptation
Jogendra Nath Kundu, Suvaansh Bhambri, Akshay Kulkarni +3
Universal Domain Adaptation (UniDA) deals with the problem of knowledge transfer between two datasets with domain-shift as well as category-shift. The goal is to categorize unlabel…
Efficient and Effective Augmentation Strategy for Adversarial Training
Sravanti Addepalli, Samyak Jain, R. Venkatesh Babu
Adversarial training of Deep Neural Networks is known to be significantly more data-hungry when compared to standard training. Furthermore, complex data augmentations such as AutoA…
Towards Efficient and Effective Self-Supervised Learning of Visual Representations
Sravanti Addepalli, Kaushal Bhogale, Priyam Dey +1
Self-supervision has emerged as a propitious method for visual representation learning after the recent paradigm shift from handcrafted pretext tasks to instance-similarity based a…
Scaling Adversarial Training to Large Perturbation Bounds
Sravanti Addepalli, Samyak Jain, Gaurang Sriramanan +1
The vulnerability of Deep Neural Networks to Adversarial Attacks has fuelled research towards building robust models. While most Adversarial Training algorithms aim at defending at…
Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks
Sravanti Addepalli, Anshul Nasery, R. Venkatesh Babu +2
Deep Neural Networks are known to be brittle to even minor distribution shifts compared to the training distribution. While one line of work has demonstrated that Simplicity Bias (…
Improving GANs for Long-Tailed Data through Group Spectral Regularization
Harsh Rangwani, Naman Jaswani, Tejan Karmali +2
Deep long-tailed learning aims to train useful deep networks on practical, real-world imbalanced distributions, wherein most labels of the tail classes are associated with a few sa…
Hierarchical Semantic Regularization of Latent Spaces in StyleGANs
Tejan Karmali, Rishubh Parihar, Susmit Agrawal +4
Progress in GANs has enabled the generation of high-resolution photorealistic images of astonishing quality. StyleGANs allow for compelling attribute modification on such images vi…
Concurrent Subsidiary Supervision for Unsupervised Source-Free Domain Adaptation
Jogendra Nath Kundu, Suvaansh Bhambri, Akshay Kulkarni +3
The prime challenge in unsupervised domain adaptation (DA) is to mitigate the domain shift between the source and target domains. Prior DA works show that pretext tasks could be us…
Segmentation Guided Deep HDR Deghosting
K. Ram Prabhakar, Susmit Agrawal, R. Venkatesh Babu
We present a motion segmentation guided convolutional neural network (CNN) approach for high dynamic range (HDR) image deghosting. First, we segment the moving regions in the input…
A Closer Look at Smoothness in Domain Adversarial Training
Harsh Rangwani, Sumukh K Aithal, Mayank Mishra +2
Domain adversarial training has been ubiquitous for achieving invariant representations and is used widely for various domain adaptation tasks. In recent times, methods converging…
Balancing Discriminability and Transferability for Source-Free Domain Adaptation
Jogendra Nath Kundu, Akshay Kulkarni, Suvaansh Bhambri +4
Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations; while concurrently preserving the task-discrimina…
Towards Data-Free Model Stealing in a Hard Label Setting
Sunandini Sanyal, Sravanti Addepalli, R. Venkatesh Babu
Machine learning models deployed as a service (MLaaS) are susceptible to model stealing attacks, where an adversary attempts to steal the model within a restricted access framework…
LEAD: Self-Supervised Landmark Estimation by Aligning Distributions of Feature Similarity
Tejan Karmali, Abhinav Atrishi, Sai Sree Harsha +3
In this work, we introduce LEAD, an approach to discover landmarks from an unannotated collection of category-specific images. Existing works in self-supervised landmark detection…
Non-Local Latent Relation Distillation for Self-Adaptive 3D Human Pose Estimation
Jogendra Nath Kundu, Siddharth Seth, Anirudh Jamkhandi +4
Available 3D human pose estimation approaches leverage different forms of strong (2D/3D pose) or weak (multi-view or depth) paired supervision. Barring synthetic or in-studio domai…
Aligning Silhouette Topology for Self-Adaptive 3D Human Pose Recovery
Mugalodi Rakesh, Jogendra Nath Kundu, Varun Jampani +1
Articulation-centric 2D/3D pose supervision forms the core training objective in most existing 3D human pose estimation techniques. Except for synthetic source environments, acquir…
Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation
Jogendra Nath Kundu, Siddharth Seth, Pradyumna YM +3
The advances in monocular 3D human pose estimation are dominated by supervised techniques that require large-scale 2D/3D pose annotations. Such methods often behave erratically in…
SISL:Self-Supervised Image Signature Learning for Splicing Detection and Localization
Susmit Agrawal, Prabhat Kumar, Siddharth Seth +3
Recent algorithms for image manipulation detection almost exclusively use deep network models. These approaches require either dense pixelwise groundtruth masks, camera ids, or ima…
Amplitude Spectrum Transformation for Open Compound Domain Adaptive Semantic Segmentation
Jogendra Nath Kundu, Akshay Kulkarni, Suvaansh Bhambri +2
Open compound domain adaptation (OCDA) has emerged as a practical adaptation setting which considers a single labeled source domain against a compound of multi-modal unlabeled targ…