Papers › Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
Integrally Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection
Feng Liu, Xiaosong Zhang, Zhiliang Peng, Zonghao Guo, Fang Wan, Xiangyang Ji, Qixiang Ye
Modern object detectors have taken the advantages of backbone networks pre-trained on large scale datasets. Except for the backbone networks, however, other components such as the detector head and the feature pyramid network (FPN) remain trained from scratch, which hinders fully tapping the potential of representation models. In this study, we propose to integrally migrate pre-trained transformer encoder-decoders (imTED) to a detector, constructing a feature extraction path which is ``fully pre-trained" so that detectors' generalization capacity is maximized. The essential differences between imTED with the baseline detector are twofold: (1) migrating the pre-trained transformer decoder to the detector head while removing the randomly initialized FPN from the feature extraction path; and (2) defining a multi-scale feature modulator (MFM) to enhance scale adaptability. Such designs not only reduce randomly initialized parameters significantly but also unify detector training with representation learning intendedly. Experiments on the MS COCO object detection dataset show that imTED consistently outperforms its counterparts by ∼2.4 AP. Without bells and whistles, imTED improves the state-of-the-art of few-shot object detection by up to 7.6 AP. Code is available at https://github.com/LiewFeng/imTED.
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 |
|---|---|---|---|---|---|---|---|
| Few-Shot Object Detection | MS-COCO (10-shot) | imTED+ViT-B | AP | 22.5 | #7 of 33 | Archive leaderboard | report |
| Few-Shot Object Detection | MS-COCO (10-shot) | imTED+ViT-S | AP | 15.0 | #18 of 33 | Archive leaderboard | report |
| Few-Shot Object Detection | MS-COCO (30-shot) | imTED+ViT-B | AP | 30.2 | #6 of 25 | Archive leaderboard | report |
| Few-Shot Object Detection | MS-COCO (30-shot) | imTED+ViT-S | AP | 21.0 | #14 of 25 | 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