Semi-Supervised Recognition under a Noisy and Fine-grained Dataset

18 Jun 2020Cheng CuiZhi YeYangxi LiXinjian LiMin YangKai WeiBing DaiYanmei ZhaoZhongji LiuRong 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... (read more)

PDF Abstract

Results from the Paper


Ranked #17 on Image Classification on ImageNet (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
BENCHMARK
Image Classification ImageNet Fix_ResNet50_vd_ssld Top 1 Accuracy 84.0% # 25
Top 5 Accuracy 97.0% # 16
Number of params 25.58M # 39
Image Classification ImageNet MobileNetV3_large_x1_0_ssld Top 1 Accuracy 79.0% # 74
Top 5 Accuracy 94.5% # 52
Number of params 5.47M # 60
Image Classification ImageNet ResNet50_vd_ssld Top 1 Accuracy 83.0% # 33
Top 5 Accuracy 96.4% # 22
Number of params 25.58M # 39
Image Classification ImageNet ResNet200_vd_26w_4s_ssld Top 1 Accuracy 85.1% # 17
Top 5 Accuracy 97.4% # 12
Number of params 76M # 19

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet