Skip to content

AMx14/Feature-Learning-Based-Knowledge-Distillation

View on GitHub ↗Related repositories →

Implemented a teacher-student framework with simple CNNs in Keras for efficient remote sensing image classification. The lightweight student model outperformed the teacher in accuracy, leveraging distillation loss and nuclear norm regularization. Validated on diverse datasets like UC Merced, EuroSat, AID, and NWPU-RESISC45.

active 2024-11-21 → 2024-12-09 (UTC)

Complete coverage28,284 / 28,284 hourly files (100%) · 2 absent upstream2023-08-15 → 2026-11-05 (UTC)
Events
3
Pushes
0
Pull requests
0
Issues
0
Stars
1
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 19 days from 2024-11-21 to 2024-12-09. Pushes: 0 total, peak 0 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 1 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Nobody pushed, opened or commented here in the loaded window — this repo's activity is stars and forks only.

Recent activity

Latest issues, pull requests and releases

No issue or PR events — this repo's activity is pushes only.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.