Papers › Semi-Supervised Recognition under a Noisy and Fine-grained Dataset
Semi-Supervised Recognition under a Noisy and Fine-grained Dataset
Cheng Cui, Zhi Ye, Yangxi Li, Xinjian Li, Min Yang, Kai Wei, Bing Dai, Yanmei Zhao, Zhongji Liu, Rong Pang
Simi-Supervised Recognition Challenge-FGVC7 is a challenging fine-grained recognition competition. One of the difficulties of this competition is how to use unlabeled data. We adopted pseudo-tag data mining to increase the amount of training data. The other one is how to identify similar birds with a very small difference, especially those have a relatively tiny main-body in examples. We combined generic image recognition and fine-grained image recognition method to solve the problem. All generic image recognition models were training using PaddleClas . Using the combination of two different ways of deep recognition models, we finally won the third place in the competition.
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 |
|---|---|---|---|---|---|---|---|
| Image Classification | ImageNet | ResNet200_vd_26w_4s_ssld | Number of params | 76M | #258 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ResNet200_vd_26w_4s_ssld | Top 1 Accuracy | 85.1% | #258 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | Fix_ResNet50_vd_ssld | Number of params | 25.58M | #364 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | Fix_ResNet50_vd_ssld | Top 1 Accuracy | 84.0% | #364 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ResNet50_vd_ssld | Number of params | 25.58M | #477 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | ResNet50_vd_ssld | Top 1 Accuracy | 83.0% | #477 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | MobileNetV3_large_x1_0_ssld | Number of params | 5.47M | #790 of 1060 | Archive leaderboard | report |
| Image Classification | ImageNet | MobileNetV3_large_x1_0_ssld | Top 1 Accuracy | 79.0% | #790 of 1060 | 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.
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