Latha Pemula
I am Latha Pemula, an Applied Scientist at AWS AILabs. I am one of the founding team members responsible for launching AWS Lookout for Vision service. My research interests include Anomaly Detection, Fewshot learning, Representation Learning, Domain Generalization. Before Amazon, I completed my Masters at Virginia Tech under the guidance of Dr. Dhruv Batra and Dr. Devi Parikh. I had a chance to work under the guidance of Dr. Lei Zhang during my internship at Microsoft Research. My masters thesis and my internship focused on fewshot classification. I completed my Bachelors in Electrical Engineering at Indian Institute of Technology, Madras(IITM) in 2010.
Research Interests
Anomaly Detection
Domain Generalization
Few-shot Classification
News
[CVPR 2024] Proposal for VAND 2.0 workshop at CVPR 2024 was accepted!
[WACV 2024] I will be presenting a keynote at the Automated Spatial And Temporal Anomaly Detection workshop at WACV 2024
[MICCAI 2023] I will be presenting a keynote at OOD workshop at MICCAI!
[CVPR 2023] Organized VAND workshop at CVPR 2022 successfully!
[ECCV 2022] Our work Spot-the-difference got accepted!
[AWARD] Our intern Karsten got EMVA Young Professional Award for his Patchcore work!
[CVPR 2022] Our work PatchCore got accepted!
[Launch] AWS Lookout For Vision launches to general public: Bloomberg News Article!
Selected work
Towards Total Recall in Industrial Anomaly Detection
We develop PatchCore - an anomaly detection method for visual product inspection, which is scalable, fast, extremely accurate, interpretable and usable without expert knowledge. Using Coreset Memories, PatchCore has retained the state-of-the-art for more than a year now.
Karsten Roth, Latha Pemula, Joaquin Zepeda, Bernhard Schoelkopf, Thomas Brox, Peter Gehler
CVPR, 2022
SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation
We release the Visual Anomaly(VisA) Dataset consisting of 10,821 high-resolution color images (9,621 normal and 1,200 anomalous samples) covering 12 objects in 3 domains, making it the largest industrial anomaly detection dataset to date. We also introduce a new self-supervised learning method for ImageNet pre-training to improve anomaly detection and segmentation in 1-class and 2-class 5/10/high shot training setups.
ECCV, 2022
We introduce learned attention models into the radio machine learning domain for the task of modulation recognition by leveraging spatial transformer networks and introducing new radio domain appropriate transformations. Using this architecture we are able to outperform our prior results in accuracy vs signal to noise ratio against an identical system without attention, however we believe such an attention model has implication far beyond the task of modulation recognition
ASILOMAR, 2016
Community Service
Reviewer for CVPR 22/23, ECCV 22, ICCV 23, TPAMI 23, WACV 22
Get in touch at latharampemula@gmail.com