San Francisco Computer Vision Meetup

This workshop provides a technical foundation for managing large scale computer vision datasets. You will learn to curate, visualize, and evaluate models using the open source FiftyOne app.

Date, Time and Location

Apr 8, 2026
10 AM PST - 11 AM Pacific
Online. Register for the Zoom!

The session covers data ingestion, embedding visualization, and model failure analysis. You will build workflows to identify dataset bias, find annotation errors, and select informative samples for training. Attendees leave with a framework for data centric AI for research and production pipelines, prioritizing data quality over pure model iteration.

What you'll learn

• Structure unstructured data. Map data and metadata into a queryable schema for images, videos, and point clouds.
• Query datasets with the FiftyOne SDK. Create complex views based on model predictions, labels, and custom tags. Use the FiftyOne to filter data based on logical conditions and confidence scores.
• Visualize high dimensional embeddings. Project features into lower dimensions to find clusters of similar samples. Identify data gaps and outliers using FiftyOne Brain.
• Automate data curation. Implement algorithmic measures to select diverse subsets for training. Reduce labeling costs by prioritizing high entropy samples.
• Debug model performance. Run evaluation routines to generate confusion matrices and precision recall curves. Visualize false positives and false negatives directly in the App to understand model failures.
• Customize FiftyOne. Build custom dashboards and interactive panels. Create specialized views for domain specific tasks.

Prerequisites:

• Working knowledge of Python and machine learning and/or computer vision fundamentals.
• All attendees will get access to the tutorials and code examples used in the workshop.

April 9, 2026 at 9 AM Pacific
Online. Register for the Zoom

Visual agents that can understand and interact with graphical user interfaces represent a transformative frontier in AI automation. These systems combine computer vision, natural language understanding, and spatial reasoning to enable machines to navigate complex interfaces—from web applications to desktop software—just as humans do. However, building robust GUI agents requires careful attention to dataset curation, model evaluation, and iterative improvement workflows.

Participants will learn how to leverage FiftyOne, an open-source toolkit for dataset curation and computer vision workflows, to build production-ready GUI agent systems.

What You'll Learn:

• Dataset Creation & Management: How to structure, annotate, and load GUI interaction datasets using the COCO4GUI standardized format
• Data Exploration & Analysis: Using FiftyOne's interactive interface to visualize datasets, analyze action distributions, and understand annotation patterns
• Multimodal Embeddings: Computing embeddings for screenshots and UI element patches to enable similarity search and retrieval
• Model Inference: Running state-of-the-art models like Microsoft's GUI-Actor to predict interaction points from natural language instructions
• Performance Evaluation: Measuring model accuracy using standard metrics and normalized click distance to assess localization precision
• Failure Analysis: Investigating model failures through attention maps, error pattern analysis, and systematic debugging workflows
• Data-Driven Improvement: Tagging samples based on error types (attention misalignment vs. localization errors) to prioritize fine-tuning efforts
• Synthetic Data Generation: Using FiftyOne plugins to augment training data with synthetic task descriptions and variations

About the Speaker

Harpreet Sahota is a hacker-in-residence and machine learning engineer with a passion for deep learning and generative AI. He’s got a deep interest in RAG, Agents, and Multimodal AI.

Apr 23, 2026
9AM PST
Online. Register for the Zoom!

Recent Advancements in Image Generation and Understanding

In this talk, I will provide an overview of my research and then take a closer look at three recent works. Image generation has progressed rapidly in the past decade-evolving from Gaussian Mixture Models (GMMs) to Variational Autoencoders (VAEs), GANs, and more recently diffusion models, which have set new standards for quality. I will begin with DiffNat (TMLR’25), which draws inspiration from a simple yet powerful observation: the kurtosis concentration property of natural images. By incorporating a kurtosis concentration loss together with a perceptual guidance strategy, DiffNat can be plugged directly into existing diffusion pipelines, leading to sharper and more faithful generations across tasks such as personalization, super-resolution, and unconditional synthesis.

Continuing the theme of improving quality under constraints, I will then discuss DuoLoRA (ICCV’25), which tackles the challenge of content–style personalization from just a few examples. DuoLoRA introduces adaptive-rank LoRA merging with cycle-consistency, allowing the model to better disentangle style from content. This not only improves personalization quality but also achieves it with 19× fewer trainable parameters, making it far more efficient than conventional merging strategies.

Finally, I will turn to Cap2Aug (WACV’25), which directly addresses data scarcity. This approach uses captions as a bridge for semantic augmentation, applying cross-modal backtranslation (image → text → image) to generate diverse synthetic samples. By aligning real and synthetic distributions, Cap2Aug boosts both few-shot and long-tail classification performance on multiple benchmarks.

About the Speaker

Aniket Roy is currently a Research Scientist at NEC Labs America. He recently earned a PhD from the Computer Science department at Johns Hopkins University under the guidance of Bloomberg Distinguished Professor Prof. Rama Chellappa.

From Representation Analysis to Data Refinement: Understanding Correlations in Deep Models

This talk examines how deep learning models encode information beyond their intended objectives and how such dependencies influence reliability, fairness, and generalization. Representation-level analysis using mutual information–based expressivity estimation is introduced to quantify the extent to which attributes such as demographics or anatomical structural factors are implicitly captured in learned embeddings, even when they are not explicitly used for supervision. These analyses reveal hierarchical patterns of attribute encoding and highlight how correlated factors emerge across layers. Data attribution techniques are then discussed to identify influential training samples that contribute to model errors and reinforce dependencies that reduce robustness. By auditing the training data through influence estimation, harmful instances can be identified and removed to improve model behavior. Together, these components highlight a unified, data-centric perspective for analyzing and refining correlations in deep models.

About the Speaker

Basudha Pal is a recent PhD graduate from the Electrical and Computer Engineering Department at Johns Hopkins University. Her research lies at the intersection of computer vision and representation learning, focusing on understanding and refining correlations in deep neural network representations for biometric and medical imaging using mutual information analysis, data attribution, and generative modeling to improve robustness, fairness, and reliability in high-stakes AI systems.

Scalable & Precise Histopathology: Next-Gen Deep Learning for Digital Histopathology

Whole slide images (WSIs) present a unique computational challenge in digital pathology, with single images reaching gigapixel resolution, equivalent to 500+ photos stitched together. This talk presents two complementary deep learning solutions for scalable and accurate WSI analysis. First, I introduce a Task-Specific Self-Supervised Learning (TS-SSL) framework that uses spatial-channel attention to learn domain-optimized feature representations, outperforming existing foundation models across multiple cancer classification benchmarks. Second, I present CEMIL, a contextual attention-based MIL framework that leverages instructor-learner knowledge distillation to classify cancer subtypes using only a fraction of WSI patches, achieving state-of-the-art accuracy with significantly reduced computational cost. Together, these methods address critical bottlenecks in generalization and efficiency for clinical-grade computational pathology.

About the Speaker

Tawsifur Rahman is a Ph.D. candidate in Biomedical Engineering at Johns Hopkins University, advised by Prof. Rama Chellappa and Dr. Alex Baras, with research focused on weakly supervised and self-supervised deep learning for computational pathology. He has completed two clinical data science internships at Johnson & Johnson MedTech and has published extensively in venues including Nature Modern Pathology, Nature Digital Medicine, MIDL, and IEEE WACV, accumulating over 8,500 citations and recognition in Stanford's Top 2% Scientists ranking.

Towards trustworthy AI under real world data challenges

The current paradigm of training AI models relies on fundamental assumptions that the data we have is clean, properly annotated, and sufficiently diverse across domains. However, this is not always true for the real world. In practice, data is may be physically corrupt, incompletely annotated, and specific to certain domains. As me move towards large scale general purpose models like LLMs and foundation models, it is even more important to address these data challenges so that we can train trustworthy AI models even with noisy real world data. In this presentation, we discuss some methods to tackle these potential issues.

About the Speaker

Ayush Gupta is a Ph.D. student at the AIEM lab, Johns Hopkins University in the department of Computer Science. He is advised by Prof. Rama Chellappa and is working on problems in Computer Vision and Deep Learning. His research has two focus points - general-purpose vision language models, where he works on multimodal LLMs on tasks like VQA, Video Grounding and LLM interpretability; and on fine-grained computer vision problems, where he works on person re-identification and gait recognition.

Apr 30, 2026
9AM - 11AM Pacific
Online. Register for the Zoom!

Zero-Shot Coreset Selection via Iterative Subspace Sampling

Deep learning's reliance on massive datasets leads to significant costs in storage, annotation, and training. Although coreset selection aims to mitigate these costs by finding performant data subsets, state-of-the-art methods typically require expensive ground-truth labels and dataset-specific training. To overcome these scalability issues, ZCore introduces a zero-shot approach that functions without labels or prior training on candidate data. Instead, ZCore uses foundation models to generate a zero-shot embedding space for unlabeled data, then quantifies the relative importance of each example based on overall coverage and redundancy within the embedding distribution. On ImageNet, ZCore outperforms previous label-based methods at a 90% prune rate while eliminating the need to annotate over one million images.

About the Speaker

Brent Griffin is a Principal Machine Learning Scientist at Voxel51 specializing in low-cost machine learning on unstructured data. Previously, he was the Perception Lead at Agility Robotics and an assistant research scientist at the University of Michigan conducting research at the intersection of computer vision, control, and robot learning. He is lead author on publications in all of the top IEEE conferences for computer vision, robotics, and control, and his work has been featured in Popular Science, in IEEE Spectrum, and on the Big Ten Network.

ENCORE: A Neural Collapse Perspective on Out of-Distribution Detection in Deep Neural Networks

We present ENCORE, a post-hoc out-of-distribution (OOD) detection method grounded in the geometric properties of neural collapse in deep neural networks. By leveraging the observation that in-distribution features align with class means while OOD features tend to be misaligned or orthogonal, ENCORE modifies inference through cosine-based scoring and adaptive feature scaling to enhance separation between known and unknown inputs. The method approximates neural collapse behavior at test time without requiring retraining, enabling more reliable uncertainty estimation. It is lightweight, memory-efficient, and compatible with a wide range of architectures, including convolutional networks and vision transformers. Extensive experiments on standard benchmarks demonstrate consistent improvements over existing OOD detection approaches in both near- and far-distribution shifts.

About the Speaker

A.Q.M. Sazzad Sayyed is a Ph.D. candidate in Electrical and Computer Engineering at Northeastern University, focusing on robust, secure, and efficient deep learning. His research centers on out-of-distribution detection, uncertainty modeling, and machine learning reliability for safety-critical and edge AI systems.

Synthesizing Compositional Videos from Text Description

Existing pre-trained text-to-video diffusion models can generate high-quality videos, but often struggle with misalignment between the generated content and the input text, particularly while composing scenes with multiple objects. To tackle this issue, we propose a straightforward, training-free approach for compositional video generation from text. We introduce Video-ASTAR for test-time aggregation and segregation of attention with a novel centroid loss to enhance alignment, which enables the generation of multiple objects in the scene, modeling the actions and interactions.

Additionally, we extend our approach to the Multi-Action video generation setting, where only the specified action should vary across a sequence of prompts. To ensure coherent action transitions, we introduce a novel token-swapping and latent interpolation strategy.

About the Speaker

Shanmuganathan Raman is a prominent academic and researcher in the fields of computer vision, deep learning, computational photography, and computer graphics. He is a Professor at the Indian Institute of Technology Gandhinagar (IIT Gandhinagar), where he holds a joint appointment in the Departments of Electrical Engineering and Computer Science and Engineering. He serves as the Head of the Department of Computer Science and Engineering at IIT Gandhinagar.

The Perceptual Observatory Characterizing Robustness and Grounding in MLLMs

Multimodal large language models can answer impressively complex visual questions, but do they truly understand what they see? We present The Perceptual Observatory, a framework for characterizing robustness and grounding in MLLMs beyond standard leaderboard scores. We evaluate models on interpretable tasks such as image matching, grid pointing game, and attribute localization across pixel-level corruptions and diffusion-based stylized illusions. Our analysis reveals that scaling the language model alone does not guarantee better perceptual grounding, uncovering systematic weaknesses in robustness, spatial invariance, fairness, and reasoning-based perception. The Perceptual Observatory offers a more principled way to study multimodal perception and provides actionable insights for building future MLLMs that are reliable and truly grounded in visual evidence.

About the Speaker

Fenil Bardoliya is a Researcher at the Complex Data Reasoning & Analysis Lab (CORAL) at Arizona State University. His research revolves around Multimodal Model Evaluation and Benchmarking, Machine Unlearning, and Structured Reasoning.