Rename compare tab labels from Base/Comparison to Old/New image.

Improve detection accuracy with full-res tiling, config flags, and evaluation.

Raise library image upload limit to 15 GB

Fix region coordinates for all formats, add Google Maps button, harden JPEG

Improve detection accuracy: TTA for AdaptFormer, hysteresis thresholding, robust logits and LBP borders.

Add compare tab tree sidebar, fix geo coordinates, and sync local folders to library.

Add detection progress bar with staged job polling for DDA compare tab.

Implement unlimited-depth tree library architecture for dev DDA.

Revert "Add zone-aware library organization for dev DDA uploads."

Add zone-aware library organization for dev DDA uploads.

Complete Phase 7: session users, RBAC, training export, and UAT hardening.

Fix DDA dev bugs and polish from full review pass.

Add Phase 5 viewer modes and Phase 6 region review with dept export.

Add colleague setup guide and env template for Change-Detection-DEV repo.

Add Phase 4 reports: PDF export, browser report page, and notification bell.

Deploy DDA jobs API, hierarchy panel, and region locate on dev.

Fix Run Detection: use /api/dda/detect/from-library and deploy compare UI.

Fix dev Space startup: add missing DDA modules referenced by local_routes.

Raise library GeoTIFF upload limit to 5 GB on dev.

HF library: auto DDA on satdetect-dev, upload to persistent storage

Fix local library scan: DDA mode in run.py, path encoding, gitignore large tifs

Use local library_sources year folders instead of web upload library

Support 2GB GeoTIFF library uploads with streamed writes and progress UI

Phase 0 DDA: APP_MODE, image library API, GeoTIFF ingest, dev UI

Align production with no-login app and refresh deploy docs

Remove login; open detection page directly

Add run.py launcher (IDLE/double-click/terminal entry point)

Add WORKFLOW.md: project workflow and onboarding guide

Fix detection precision: gated fusion, strict registration, calibrated thresholds, preload model

Fix: rename models/ to cd_models/ to avoid shadowing app/models.py (SQLAlchemy User model)

Add SIFT+FLANN registration, Siamese U-Net, multi-scale detection, ExG vegetation, Hybrid AI mode, confidence maps

Improve building detection: fix tile size to 256, lower thresholds, add SSIM, smarter scoring

Fix: add einops dependency required by AdaptFormer custom code

Fix: add trust_remote_code=True for AdaptFormer custom model code

Production overhaul: pre-trained AdaptFormer model + detection quality improvements

Optimize notebook for CPU training: MobileNetV2 encoder, 15 epochs, batch 4

Fix notebook: use HuggingFace datasets CDN instead of flaky Google Drive links

Add Siamese U-Net training notebook and model inference integration

Clean visualization: subtle tint overlay, outline-only boxes, 30-region cap, high-contrast labels

Redesign detection pipeline: CVA, vegetation/shadow suppression, SNR fusion, multi-scale SSIM

Thinner, more precise detection lines and compact labels

Restore Method dropdown, Image Registration and Radiometric Normalization options

Force cache bust - bump APP_BUILD, CSS and JS versions

Remove method/model selection UI - use AI-Based Deep Learning by default

Revert to satellite change detection only - remove landslide, pothole, detection type menu

Pothole YOLO pipeline: single-image mode, modular detector, red box visualization

Add pothole detection as new menu type with separate engine and research plan

HF runtime fix: bind uvicorn to dynamic PORT env

UX: always land on detection-type menu after login

Fix detection-type menu navigation: switch mode and dashboard without reload loop