Papers › MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection
MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection
Jongmok Kim, Jooyoung Jang, Seunghyeon Seo, Jisoo Jeong, Jongkeun Na, Nojun Kwak
Many recent semi-supervised learning (SSL) studies build teacher-student architecture and train the student network by the generated supervisory signal from the teacher. Data augmentation strategy plays a significant role in the SSL framework since it is hard to create a weak-strong augmented input pair without losing label information. Especially when extending SSL to semi-supervised object detection (SSOD), many strong augmentation methodologies related to image geometry and interpolation-regularization are hard to utilize since they possibly hurt the location information of the bounding box in the object detection task. To address this, we introduce a simple yet effective data augmentation method, Mix/UnMix (MUM), which unmixes feature tiles for the mixed image tiles for the SSOD framework. Our proposed method makes mixed input image tiles and reconstructs them in the feature space. Thus, MUM can enjoy the interpolation-regularization effect from non-interpolated pseudo-labels and successfully generate a meaningful weak-strong pair. Furthermore, MUM can be easily equipped on top of various SSOD methods. Extensive experiments on MS-COCO and PASCAL VOC datasets demonstrate the superiority of MUM by consistently improving the mAP performance over the baseline in all the tested SSOD benchmark protocols.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
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 |
|---|---|---|---|---|---|---|---|
| Semi-Supervised Object Detection | COCO 0.5% labeled data | MUM | mAP | 18.54 | #4 of 5 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 1% labeled data | MUM | mAP | 21.88 | #13 of 22 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 10% labeled data | MUM | mAP | 31.87 | #21 of 27 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 100% labeled data | MUM | mAP | 42.11 | #10 of 13 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 2% labeled data | MUM | mAP | 24.84 | #12 of 19 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 5% labeled data | MUM | mAP | 28.52 | #18 of 23 | 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