publications

2026

1. Preprint

   MetaLoRA: Image-Based LoRA Initialization with Metacognition for Test-Time Adaptation

   D. Manjunath, Aniruddh Sikdar, Junaid, and 1 more author

   2026

   Under review
2. Preprint

   ASGARD: Bridging the Ground-Aerial Gap with Spatial-Enhanced LoRA and Global Domain Navigation for Test-Time Adaptation

   Aniruddh Sikdar, D. Manjunath, Smruti Sekhar, and 1 more author

   2026

   Under review
3. Preprint

   T-CAT: Toggle as You Tune for Open Vocabulary Semantic Segmentation

   Aniruddh Sikdar, Aditya Gandhamal, and Suresh Sundaram

   2026

   Under review · Transactions on Machine Learning Research (TMLR)
4. Preprint

   Hi-DETR: Hierarchically Integrated Transformer for Efficient Small Object Detection

   Ahish Vasist, Rohit Sala, Qiranul Saddyean, and 3 more authors

   2026

   Under review · Expert Systems with Applications
5. ECCVW

   

   CROMPT: Adapting CLIP via Cross-Modal Prompting for Robust Zero-Shot Generalization under Adverse Weather

   Aniruddh Sikdar, Arya Kishor, Snehashis Dhibar, and 1 more author

   In Proceedings of the European Conference on Computer Vision Workshops (ECCVW), 2nd Workshop on Multimodal Reasoning and Slow Thinking in the Large Model Era: Towards System 2 and Beyond, 2026
6. ECCVW

   

   Pixel2Perspective: A Benchmark for Multi-Modal and Multi-View Generalization in Vision-Language Models

   Aditya Gandhamal, Aniruddh Sikdar, Arya Kishor, and 1 more author

   In Proceedings of the European Conference on Computer Vision Workshops (ECCVW), 2nd Workshop on Multimodal Reasoning and Slow Thinking in the Large Model Era: Towards System 2 and Beyond, 2026
7. IROS

   

   CoLoRA: Optimal Transport Meets LoRA for Multi-Domain Open-Vocabulary Segmentation

   Aniruddh Sikdar, Aditya Gandhamal, and Suresh Sundaram

   In 2026 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2026

   Website

2025

1. PhD Thesis

   

   Development of Perception Systems to Enhance Robustness for Robotic Applications

   Aniruddh Sikdar

   Indian Institute of Science, 2025
2. CVPRW

   

   Picazo: Pixel‑Aligned Contrastive Learning for Zero‑Shot Domain Adaptation

   Aniruddh Sikdar, Arya Kishor, Ishika Kadam, and 1 more author

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025

   Oral Presentation (Top 15.38%) Video

   true

3. CVPRW

   

   SAGA: Semantic‑Aware Gray Color Augmentation for Visible‑to‑Thermal Domain Adaptation Across Multi‑View Drone and Ground‑Based Vision Systems

   D. Manjunath, Aniruddh Sikdar, Prajwal Gurunath, and 2 more authors

   In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025

   Video
4. CVPRW

   

   VISTA‑CLIP: Visual Incremental Self‑Tuned Adaptation for Efficient Continual Panoptic Segmentation

   D. Manjunath, Shrikar Madhu, Aniruddh Sikdar, and 1 more author

   In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2025
5. CVPRW

   

   OV‑COAST: Cost Aggregation with Optimal Transport for Open‑Vocabulary Semantic Segmentation

   Aditya Gandhamal, Aniruddh Sikdar, and Suresh Sundaram

   In Workshop on Transformers for Vision at CVPR 2025 (Non‑archival Track), 2025

   Accepted (Non‑archival)

   Code Website
6. CVPRW

   

   AetherVision‑Bench: An Open‑Vocabulary RGB‑Infrared Benchmark for Multi‑Angle Segmentation across Aerial and Ground Perspectives

   Aniruddh Sikdar, Aditya Gandhamal, and Suresh Sundaram

   In Workshop on Foundation Models Meet Embodied Agents at CVPR 2025 (Non‑archival Track), 2025

   Accepted (Non‑archival)

   Website
7. IEEE GRSL

   

   Syn2Real Domain Generalization for Underwater Mine‑Like Object Detection Using Side‑Scan Sonar

   Aayush Agrawal, Aniruddh Sikdar, Rajini Makam, and 3 more authors

   IEEE Geoscience and Remote Sensing Letters, 2025
8. ETAAV

   

   Domain Generalization for Environmental Uncertainties Using Metacognitive Mask R‑CNN

   Sayan Chaudhuri, Aniruddh Sikdar, and Suresh Sundaram

   In 2025 International Conference on Emerging Technology in Autonomous Aerial Vehicles (ETAAV), 2025
9. AAAI

   

   OGP-Net: Optical Guidance Meets Pixel-Level Contrastive Distillation for Robust Multi-Modal and Missing Modality Segmentation

   Aniruddh Sikdar, Jayant Teotia, and Suresh Sundaram

   In Proceedings of the AAAI Conference on Artificial Intelligence, 2025

   Video

2024

1. IROS

   

   SSL-RGB2IR: Semi-Supervised RGB-to-IR Image-to-Image Translation for Enhancing Visual Task Training in Semantic Segmentation and Object Detection

   Aniruddh Sikdar, Qiranul Saadiyean, Prahlad Anand, and 1 more author

   In 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024
2. CVPR

   

   MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation

   Sumanth Udupa, Prajwal Gurunath, Aniruddh Sikdar, and 1 more author

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

   Video
3. ICRA

   

   SKD-Net: Spectral-Based Knowledge Distillation in Low-Light Thermal Imagery for Robotic Perception

   Aniruddh Sikdar, Jayant Teotia, and Suresh Sundaram

   In 2024 IEEE International Conference on Robotics and Automation (ICRA), 2024

2023

1. CVPRW

   

   DeepMAO: Deep Multi-Scale Aware Overcomplete Network for Building Segmentation in Satellite Imagery

   Aniruddh Sikdar, Sumanth Udupa, Suresh Sundaram, and 1 more author

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2023

   Video
2. ICASSP

   

   Fully Complex-Valued Deep Learning Model for Visual Perception

   Aniruddh Sikdar, Sumanth Udupa, and Suresh Sundaram

   In 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023

   Oral Presentation (Top 23%) Video

   true

2022

1. SSCI

   

   Fully complex-valued fully convolutional multi-feature fusion network (fc2mfn) for building segmentation of insar images

   Aniruddh Sikdar, Sumanth Udupa, Suresh Sundaram, and 1 more author

   In 2022 IEEE Symposium Series on Computational Intelligence (SSCI), 2022