Papers › Fer2013 Recognition - ResNet18 With Tricks
Fer2013 Recognition - ResNet18 With Tricks
Xiaojian Yuan
This work is the final project of the Computer Vision Course of USTC. However, I achieve the highest single-network classification accuracy on FER2013 based on ResNet18. To my best knowledge, this work achieves state-of-the-art single-network accuracy of 73.70 % on FER2013 without using extra training data, which exceeds the previous work [1] of 73.28%.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Facial Expression Recognition (FER) | FER2013 | ResNet18 With Tricks | Accuracy | 73.70 | #11 of 17 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections