Manogna Sreenivas

I am currently pursuing my PhD at the Department of Electrical Engineering, IISc, Bangalore. I work at the IACV lab under the supervision of Dr. Soma Biswas.

Prior to this, I worked as a Software Engineer at PathPartner Technology, Bangalore for about three years. I graduated with a B.Tech in Electrical and Electronics Engineering from NITK Surathkal in 2017.

I am interested in applying learning methods to solve computer vision problems, where one has access to only limited data and can encounter distribution shifts. Over the course of my PhD, I aim to develop methods capable of learning and adapting in such dynamic real-world environments with less data and compute power.

selected publications

arXiV

Effectiveness of Vision Language Models for Open-world Single Image Test Time Adaptation

Manogna Sreenivas, and Soma Biswas

In PrePrint. Under Review, 2024

Abs arXiv Code Website

We propose a novel framework to address the real-world challenging task of Single Image Test Time Adaptation in an open and dynamic environment. We leverage large scale Vision Language Models like CLIP to enable real time adaptation on a per-image basis without access to source data or ground truth labels. Since the deployed model can also encounter unseen classes in an open world, we first employ a simple and effective Out of Distribution (OOD) detection module to distinguish between weak and strong OOD samples. We propose a novel contrastive learning based objective to enhance the discriminability between weak and strong OOD samples by utilizing small, dynamically updated feature banks. Finally, we also employ a classification objective for adapting the model using the reliable weak OOD samples. The proposed framework ROSITA combines these components, enabling continuous online adaptation of Vision Language Models on a single image basis. Extensive experimentation on diverse domain adaptation benchmarks validates the effectiveness of the proposed framework.
WACV

pSTarC: Pseudo Source Guided Target Clustering for Fully Test-Time Adaptation

Manogna Sreenivas, Goirik Chakrabarty, and Soma Biswas

In Winter Conference on Applications of Computer Vision, 2024

Abs arXiv Code Website

Test Time Adaptation (TTA) is a pivotal concept in machine learning, enabling models to perform well in real-world scenarios, where test data distribution differs from training. In this work, we propose a novel approach called pseudo Source guided Target Clustering (pSTarC) addressing the relatively unexplored area of TTA under real-world domain shifts. This method draws inspiration from target clustering techniques and exploits the source classifier for generating pseudo-source samples. The test samples are strategically aligned with these pseudo-source samples, facilitating their clustering and thereby enhancing TTA performance. pSTarC operates solely within the fully test-time adaptation protocol, removing the need for actual source data. Experimental validation on a variety of domain shift datasets, namely VisDA, Office-Home, DomainNet-126, CIFAR-100C verifies pSTarC’s effectiveness. This method exhibits significant improvements in prediction accuracy along with efficient computational requirements. Furthermore, we also demonstrate the universality of the pSTarC framework by showing its effectiveness for the continuous TTA framework.
TMLR

SANTA: Source Anchoring Network and Target Alignment for Continual Test Time Adaptation

Goirik Chakrabarty, Manogna Sreenivas, and Soma Biswas

In Transactions in Machine Learning Research, 2023

Abs HTML PDF Code

Adapting a trained model to perform satisfactorily on continually changing test environ- ments is an important and challenging task. In this work, we propose a novel framework, SANTA, which aims to satisfy the following characteristics required for online adaptation: 1) can work effectively for different (even small) batch sizes; 2) should continue to work well on the source domain; 3) should have minimal tunable hyperparameters and storage requirements. Given a pre-trained network trained on source domain data, the proposed framework modifies the affine parameters of the batch normalization layers using source anchoring based self-distillation. This ensures that the model incorporates knowledge from the newly encountered domains, without catastrophically forgetting the previously seen do- mains. We also propose a source-prototype driven contrastive alignment to ensure natural grouping of the target samples, while maintaining the already learnt semantic information. Extensive evaluation on three benchmark datasets under challenging settings justify the effectiveness of SANTA for real-world applications.