CV

Education

B.S. in GitHub, GitHub University, 2012
M.S. in Jekyll, GitHub University, 2014
Ph.D in Version Control Theory, GitHub University, 2018 (expected)

Work experience

Summer 2015: Research Assistant
- Github University
- Duties included: Tagging issues
- Supervisor: Professor Git
Fall 2015: Research Assistant
- Github University
- Duties included: Merging pull requests
- Supervisor: Professor Hub

Skills

Skill 1
Skill 2
- Sub-skill 2.1
- Sub-skill 2.2
- Sub-skill 2.3
Skill 3

Publications

Optical flow estimation & segmentation of multiple moving dynamic textures

Rene Vidal and Avinash Ravichandran (2005). "Optical flow estimation & segmentation of multiple moving dynamic textures" CVPR 2005.

Segmenting a beating heart using polysegment and spatial GPCA

Avinash Ravichandran and René Vidal and Henry Halperin (2006). "Segmenting a beating heart using polysegment and spatial GPCA" ISBI 2006.

Mosaicing nonrigid dynamical scenes

Avinash Ravichandran and René Vidal (2007). "Mosaicing nonrigid dynamical scenes" Proc. Workshop Dynamic Vision.

Video Registration Using Dynamic Textures

Avinash Ravichandran and Rene Vidal (2008). "Video Registration Using Dynamic Textures" ECCV 2008.

Histograms of oriented optical flow and binet-cauchy kernels on nonlinear dynamical systems for the recognition of human actions

Rizwan Chaudhry and Avinash Ravichandran and Gregory Hager and René Vidal (2009). "Histograms of oriented optical flow and binet-cauchy kernels on nonlinear dynamical systems for the recognition of human actions" IEEE.

View-invariant dynamic texture recognition using a bag of dynamical systems

Avinash Ravichandran and Rizwan Chaudhry and René Vidal (2009). "View-invariant dynamic texture recognition using a bag of dynamical systems" CVPR 2009.

A unified approach to segmentation and categorization of dynamic textures

Avinash Ravichandran and Paolo Favaro and René Vidal (2010). "A unified approach to segmentation and categorization of dynamic textures" Springer Berlin Heidelberg.

Categorizing video sequences of non-rigid dynamical objects

Avinash Aghoram Ravichandran (2010). "Categorizing video sequences of non-rigid dynamical objects" Unknown Venue.

A closed form solution to robust subspace estimation and clustering

Paolo Favaro and René Vidal and Avinash Ravichandran (2011). "A closed form solution to robust subspace estimation and clustering" CVPR 2011.

Categorizing Dynamic Textures using a Bag of Dynamical Systems

Avinash Ravichandran and Rizwan Chaudhry and Rene Vidal (2012). "Categorizing Dynamic Textures using a Bag of Dynamical Systems" IEEE Transactions on Pattern Analysis and Machine Intelligence.

Encoding scene structures for video compression

Georgios Georgiadis and Avinash Ravichandran and Stefano Soatto and Alessandro Chiuso (2012). "Encoding scene structures for video compression" SPIE.

Group action induced distances for averaging and clustering Linear Dynamical Systems with applications to the analysis of dynamic scenes

Bijan Afsari and Rizwan Chaudhry and Avinash Ravichandran and René Vidal (2012). "Group action induced distances for averaging and clustering Linear Dynamical Systems with applications to the analysis of dynamic scenes" CVPR 2012.

Image Priors for Image Deblurring with Uncertain Blur.

Daniele Perrone and Avinash Ravichandran and René Vidal and Paolo Favaro (2012). "Image Priors for Image Deblurring with Uncertain Blur." BMVC.

Long-range spatio-temporal modeling of video with application to fire detection

Avinash Ravichandran and Stefano Soatto (2012). "Long-range spatio-temporal modeling of video with application to fire detection" Springer Berlin Heidelberg.

Superfloxels: A mid-level representation for video sequences

Avinash Ravichandran and Chaohui Wang and Michalis Raptis and Stefano Soatto (2012). "Superfloxels: A mid-level representation for video sequences" ECCV 2012 workshops.

Semantic video segmentation from occlusion relations within a convex optimization framework

Brian Taylor and Alper Ayvaci and Avinash Ravichandran and Stefano Soatto (2013). "Semantic video segmentation from occlusion relations within a convex optimization framework" Springer Berlin Heidelberg.

Active frame, location, and detector selection for automated and manual video annotation

Vasiliy Karasev and Avinash Ravichandran and Stefano Soatto (2014). "Active frame, location, and detector selection for automated and manual video annotation" Tech Report UCLACSD140010, 2014. 4.

Dynamical Systems in Video Analysis

Gianfranco Doretto and Avinash Ravichandran and René Vidal and Stefano Soatto (2014). "Dynamical Systems in Video Analysis" Elsevier.

Recognizing three-dimensional objects

Oleg Rybakov and Avinash Aghoram Ravichandran and Matias Omar Gregorio Benitez (2015). "Recognizing three-dimensional objects" .

System and method for aligning video sequences

Rene Esteban Vidal and Avinash Aghoram Ravichandran (2015). "System and method for aligning video sequences" .

Approaches for scene-based object tracking

Oleg Rybakov and Avinash Aghoram Ravichandran and Daniel Bibireata and Ajay Kumar Mishra and Wei Zhang (2017). "Approaches for scene-based object tracking" .

Cluster-trained machine learning for image processing

Marshall Friend Tappen and Avinash Aghoram Ravichandran and Hakan Boyraz and Baoyuan Liu (2017). "Cluster-trained machine learning for image processing" .

Object recognition

Avinash Aghoram Ravichandran and Matias Omar Gregorio Benitez and Rahul Bhotika and Scott Daniel Helmer and Anshul Kumar Jain and Junxiong Jia and Rakesh Madhavan Nambiar and Oleg Rybakov (2017). "Object recognition" .

A baseline for few-shot image classification

Guneet S Dhillon and Pratik Chaudhari and Avinash Ravichandran and Stefano Soatto (2019). "A baseline for few-shot image classification" arXiv preprint arXiv:1909.02729.

Few-shot learning with embedded class models and shot-free meta training

Avinash Ravichandran and Rahul Bhotika and Stefano Soatto (2019). "Few-shot learning with embedded class models and shot-free meta training" Proceedings of the IEEE/CVF international conference on computer vision.

Meta-learning with differentiable convex optimization

Kwonjoon Lee and Subhransu Maji and Avinash Ravichandran and Stefano Soatto (2019). "Meta-learning with differentiable convex optimization" Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.

Object recognition

Task2vec: Task embedding for meta-learning

Alessandro Achille and Michael Lam and Rahul Tewari and Avinash Ravichandran and Subhransu Maji and Charless C Fowlkes and Stefano Soatto and Pietro Perona (2019). "Task2vec: Task embedding for meta-learning" Proceedings of the IEEE/CVF international conference on computer vision.

Unbiased evaluation of deep metric learning algorithms

Istvan Fehervari and Avinash Ravichandran and Srikar Appalaraju (2019). "Unbiased evaluation of deep metric learning algorithms" arXiv preprint arXiv:1911.12528.

A baseline for few-shot image classiﬁcation

Guneet Singh Dhillon and Pratik Chaudhari and Avinash Ravichandran and Stefano Soatto (2020). "A baseline for few-shot image classiﬁcation" ICLR 2020.

Continual universal object detection

Xialei Liu and Hao Yang and Avinash Ravichandran and Rahul Bhotika and Stefano Soatto (2020). "Continual universal object detection" arXiv preprint arXiv:2002.05347.

Dynamically scaled training fleets for machine learning

Leo Parker Dirac and Rakesh Madhavan Nambiar and Avinash Aghoram Ravichandran (2020). "Dynamically scaled training fleets for machine learning" .

Incremental few-shot meta-learning via indirect discriminant alignment

Qing Liu and Orchid Majumder and Alessandro Achille and Avinash Ravichandran and Rahul Bhotika and Stefano Soatto (2020). "Incremental few-shot meta-learning via indirect discriminant alignment" ECCV 2020.

Incremental learning for metric-based meta-learners

Qing Liu and Orchid Majumder and Avinash Ravichandran and Rahul Bhotika and Stefano Soatto (2020). "Incremental learning for metric-based meta-learners" ArXiv, abs/2002.04162.

Incremental meta-learning via indirect discriminant alignment

Qing Liu and Orchid Majumder and Alessandro Achille and Avinash Ravichandran and Rahul Bhotika and Stefano Soatto (2020). "Incremental meta-learning via indirect discriminant alignment" arXiv preprint arXiv:2002.04162.

Multi-task incremental learning for object detection

Xialei Liu and Hao Yang and Avinash Ravichandran and Rahul Bhotika and Stefano Soatto (2020). "Multi-task incremental learning for object detection" arXiv preprint arXiv:2002.05347.

Parts-based visual similarity search

Avinash Aghoram Ravichandran and Michael Quang Thai Lam and Rahul Bhotika (2020). "Parts-based visual similarity search" .

Predicting training time without training

Luca Zancato and Alessandro Achille and Avinash Ravichandran and Rahul Bhotika and Stefano Soatto (2020). "Predicting training time without training" Advances in Neural Information Processing Systems.

Rethinking the hyperparameters for fine-tuning

Hao Li and Pratik Chaudhari and Hao Yang and Michael Lam and Avinash Ravichandran and Rahul Bhotika and Stefano Soatto (2020). "Rethinking the hyperparameters for fine-tuning" arXiv preprint arXiv:2002.11770.

Visual similarity and attribute manipulation using deep neural networks

Rahul Bhotika and Avinash Aghoram Ravichandran (2020). "Visual similarity and attribute manipulation using deep neural networks" .

A linearized framework and a new benchmark for model selection for fine-tuning

Aditya Deshpande and Alessandro Achille and Avinash Ravichandran and Hao Li and Luca Zancato and Charless Fowlkes and Rahul Bhotika and Stefano Soatto and Pietro Perona (2021). "A linearized framework and a new benchmark for model selection for fine-tuning" arXiv preprint arXiv:2102.00084.

Diva: Dataset derivative of a learning task

Yonatan Dukler and Alessandro Achille and Giovanni Paolini and Avinash Ravichandran and Marzia Polito and Stefano Soatto (2021). "Diva: Dataset derivative of a learning task" arXiv preprint arXiv:2111.09785.

Estimating informativeness of samples with smooth unique information

Hrayr Harutyunyan and Alessandro Achille and Giovanni Paolini and Orchid Majumder and Avinash Ravichandran and Rahul Bhotika and Stefano Soatto (2021). "Estimating informativeness of samples with smooth unique information" arXiv preprint arXiv:2101.06640.

Exponential moving average normalization for self-supervised and semi-supervised learning

Zhaowei Cai and Avinash Ravichandran and Subhransu Maji and Charless Fowlkes and Zhuowen Tu and Stefano Soatto (2021). "Exponential moving average normalization for self-supervised and semi-supervised learning" Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.

Lqf: Linear quadratic fine-tuning

Alessandro Achille and Aditya Golatkar and Avinash Ravichandran and Marzia Polito and Stefano Soatto (2021). "Lqf: Linear quadratic fine-tuning" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Mixed-privacy forgetting in deep networks

Aditya Golatkar and Alessandro Achille and Avinash Ravichandran and Marzia Polito and Stefano Soatto (2021). "Mixed-privacy forgetting in deep networks" Proceedings of the IEEE/CVF conference on computer vision and pattern recognition.

Prototypical network algorithms for few-shot learning

Avinash Aghoram Ravichandran and Paulo Ricardo dos Santos Mendonca and Rahul Bhotika and Stefano Soatto (2021). "Prototypical network algorithms for few-shot learning" .

Representation consolidation for training expert students

Zhizhong Li and Avinash Ravichandran and Charless Fowlkes and Marzia Polito and Rahul Bhotika and Stefano Soatto (2021). "Representation consolidation for training expert students" arXiv preprint arXiv:2107.08039.

Revisiting contrastive learning for few-shot classification

Orchid Majumder and Avinash Ravichandran and Subhransu Maji and Marzia Polito and Rahul Bhotika and Stefano Soatto (2021). "Revisiting contrastive learning for few-shot classification" arXiv preprint.

Supervised momentum contrastive learning for few-shot classification

Orchid Majumder and Avinash Ravichandran and Subhransu Maji and Alessandro Achille and Marzia Polito and Stefano Soatto (2021). "Supervised momentum contrastive learning for few-shot classification" arXiv preprint arXiv:2101.11058.

Uniform sampling over episode difficulty

Sébastien Arnold and Guneet Dhillon and Avinash Ravichandran and Stefano Soatto (2021). "Uniform sampling over episode difficulty" Advances in Neural Information Processing Systems.

Automated model selection for network-based image recognition service

Avinash Aghoram Ravichandran and Rahul Bhotika and Stefano Soatto and Pietro Perona and Hao Yang (2022). "Automated model selection for network-based image recognition service" .

Class-incremental learning with strong pre-trained models

Tz-Ying Wu and Gurumurthy Swaminathan and Zhizhong Li and Avinash Ravichandran and Nuno Vasconcelos and Rahul Bhotika and Stefano Soatto (2022). "Class-incremental learning with strong pre-trained models" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Completr: Reducing the cost of annotations for object detection in dense scenes with vision transformers

Achin Jain and Kibok Lee and Gurumurthy Swaminathan and Hao Yang and Bernt Schiele and Avinash Ravichandran and Onkar Dabeer (2022). "Completr: Reducing the cost of annotations for object detection in dense scenes with vision transformers" arXiv preprint arXiv:2209.05654.

Masked vision and language modeling for multi-modal representation learning

Gukyeong Kwon and Zhaowei Cai and Avinash Ravichandran and Erhan Bas and Rahul Bhotika and Stefano Soatto (2022). "Masked vision and language modeling for multi-modal representation learning" arXiv preprint arXiv:2208.02131.

Rethinking few-shot object detection on a multi-domain benchmark

Kibok Lee and Hao Yang and Satyaki Chakraborty and Zhaowei Cai and Gurumurthy Swaminathan and Avinash Ravichandran and Onkar Dabeer (2022). "Rethinking few-shot object detection on a multi-domain benchmark" ECCV 2022.

Semi-supervised vision transformers at scale

Zhaowei Cai and Avinash Ravichandran and Paolo Favaro and Manchen Wang and Davide Modolo and Rahul Bhotika and Zhuowen Tu and Stefano Soatto (2022). "Semi-supervised vision transformers at scale" Advances in Neural Information Processing Systems.

Task adaptive parameter sharing for multi-task learning

Matthew Wallingford and Hao Li and Alessandro Achille and Avinash Ravichandran and Charless Fowlkes and Rahul Bhotika and Stefano Soatto (2022). "Task adaptive parameter sharing for multi-task learning" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

X-detr: A versatile architecture for instance-wise vision-language tasks

Zhaowei Cai and Gukyeong Kwon and Avinash Ravichandran and Erhan Bas and Zhuowen Tu and Rahul Bhotika and Stefano Soatto (2022). "X-detr: A versatile architecture for instance-wise vision-language tasks" ECCV 2022.

A meta-learning approach to predicting performance and data requirements

Achin Jain and Gurumurthy Swaminathan and Paolo Favaro and Hao Yang and Avinash Ravichandran and Hrayr Harutyunyan and Alessandro Achille and Onkar Dabeer and Bernt Schiele and Ashwin Swaminathan and Stefano Soatto (2023). "A meta-learning approach to predicting performance and data requirements" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Dynamically scaled training fleets for machine learning

Leo Parker Dirac and Rakesh Madhavan Nambiar and Avinash Aghoram Ravichandran (2023). "Dynamically scaled training fleets for machine learning" .

Introspective cross-attention probing for lightweight transfer of pre-trained models

Yonatan Dukler and Alessandro Achille and Hao Yang and Varsha Vivek and Luca Zancato and Benjamin Bowman and Avinash Ravichandran and Charless C Fowlkes and Ashwin Swaminathan and Stefano Soatto (2023). "Introspective cross-attention probing for lightweight transfer of pre-trained models" CoRR.

Learning expressive prompting with residuals for vision transformers

Rajshekhar Das and Yonatan Dukler and Avinash Ravichandran and Ashwin Swaminathan (2023). "Learning expressive prompting with residuals for vision transformers" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Winclip: Zero-/few-shot anomaly classification and segmentation

Jongheon Jeong and Yang Zou and Taewan Kim and Dongqing Zhang and Avinash Ravichandran and Onkar Dabeer (2023). "Winclip: Zero-/few-shot anomaly classification and segmentation" Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.

Your representations are in the network: composable and parallel adaptation for large scale models

Yonatan Dukler and Alessandro Achille and Hao Yang and Varsha Vivek and Luca Zancato and Benjamin Bowman and Avinash Ravichandran and Charless Fowlkes and Ashwin Swaminathan and Stefano Soatto (2023). "Your representations are in the network: composable and parallel adaptation for large scale models" Advances in Neural Information Processing Systems.

Anomaly detection using feedback training

Barath Balasubramanian and Rahul Bhotika and Niels Brouwers and Ranju Das and Prakash Krishnan and Shaun Ryan James MCDOWELL and Anushri MAINTHIA and Rakesh Madhavan Nambiar and Anant Patel and Avinash Aghoram Ravichandran and Joaquin Zepeda Salvatierra and Gurumurthy Swaminathan (2024). "Anomaly detection using feedback training" .

CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning

Runjian Chen and Hang Zhang and Avinash Ravichandran and Hyoungseob Park and Wenqi Shao and Alex Wong and Ping Luo (2024). "CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning" arXiv preprint arXiv:2412.03059.

Feedback-based training for anomaly detection

Genmm: Geometrically and temporally consistent multimodal data generation for video and lidar

Bharat Singh and Viveka Kulharia and Luyu Yang and Avinash Ravichandran and Ambrish Tyagi and Ashish Shrivastava (2024). "Genmm: Geometrically and temporally consistent multimodal data generation for video and lidar" arXiv preprint arXiv:2406.10722.

Invi: Object insertion in videos using off-the-shelf diffusion models

Nirat Saini and Navaneeth Bodla and Ashish Shrivastava and Avinash Ravichandran and Xiao Zhang and Abhinav Shrivastava and Bharat Singh (2024). "Invi: Object insertion in videos using off-the-shelf diffusion models" arXiv preprint arXiv:2407.10958.

Vlm-kd: Knowledge distillation from vlm for long-tail visual recognition

Zaiwei Zhang and Gregory P Meyer and Zhichao Lu and Ashish Shrivastava and Avinash Ravichandran and Eric M Wolff (2024). "Vlm-kd: Knowledge distillation from vlm for long-tail visual recognition" arXiv preprint arXiv:2408.16930.

Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation

Reza Akbarian Bafghi and Carden Bagwell and Avinash Ravichandran and Ashish Shrivastava and Maziar Raissi (2025). "Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation" arXiv e-prints.

Training Domain Draft Models for Speculative Decoding: Best Practices and Insights

Fenglu Hong and Ravi Raju and Jonathan Lingjie Li and Bo Li and Urmish Thakker and Avinash Ravichandran and Swayambhoo Jain and Changran Hu (2025). "Training Domain Draft Models for Speculative Decoding: Best Practices and Insights" arXiv preprint arXiv:2503.07807.

Avinash Ravichandran

CV

Education

Work experience

Skills

Publications

Talks

Teaching

Service and leadership