Blog

Thoughts on ML, computer vision, and AI research

Circuit Extraction: Interpreting Object Detectors

January 13, 2026 • 14 min read

Using activation patching and co-activation analysis to extract the minimal computational circuit for pot detection in Faster R-CNN.

Object Detection on Drone Orthomosaics with SAM

January 10, 2026 • 8 min read

An overview of using Meta's Segment Anything Model for automated object detection in high-resolution aerial imagery, with applications in precision agriculture.

Sparse Linear Probing for Efficient Detection

January 9, 2026 • 10 min read

Using L1-regularized linear probes to identify minimal feature subsets from SAM and Faster R-CNN that are sufficient for pot detection.

Extracting Features from Vision Model Backbones

January 7, 2026 • 12 min read

A technical guide to extracting and visualizing internal representations from SAM and Faster R-CNN for interpretability research.

Mechanistic Interpretability for Agricultural AI

January 5, 2026 • 10 min read

Exploring how mechanistic interpretability techniques can help us understand what vision models learn about agricultural environments and build more trustworthy AI systems.

SAM vs Faster R-CNN: A Practical Comparison

January 3, 2026 • 10 min read

Comparing Segment Anything Model and Faster R-CNN for aerial object detection—architecture, fine-tuning approaches, and when to use each.

Fine-Tuning Vision Foundation Models

December 28, 2025 • 12 min read

A practical guide to fine-tuning strategies for vision models like SAM and Faster R-CNN, with insights on data efficiency and domain adaptation.

Building a GeoTIFF Object Detection Web App

December 28, 2025 • 5 min read

A walkthrough of building a web application for running Faster R-CNN inference on geospatial imagery with FastAPI, WebSockets, and Leaflet.

Training Faster R-CNN for Geospatial Object Detection

December 20, 2025 • 8 min read

A deep dive into training object detection models on aerial imagery, from SAM masks to production-ready Faster R-CNN with hard negative mining.