Papers › Semi-Supervised Domain Generalization for Object Detection via Language-Guided Feature...
Semi-Supervised Domain Generalization for Object Detection via Language-Guided Feature Alignment
Sina Malakouti, Adriana Kovashka
Existing domain adaptation (DA) and generalization (DG) methods in object detection enforce feature alignment in the visual space but face challenges like object appearance variability and scene complexity, which make it difficult to distinguish between objects and achieve accurate detection. In this paper, we are the first to address the problem of semi-supervised domain generalization by exploring vision-language pre-training and enforcing feature alignment through the language space. We employ a novel Cross-Domain Descriptive Multi-Scale Learning (CDDMSL) aiming to maximize the agreement between descriptions of an image presented with different domain-specific characteristics in the embedding space. CDDMSL significantly outperforms existing methods, achieving 11.7% and 7.5% improvement in DG and DA settings, respectively. Comprehensive analysis and ablation studies confirm the effectiveness of our method, positioning CDDMSL as a promising approach for domain generalization in object detection tasks.
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 |
|---|---|---|---|---|---|---|---|
| Object Detection | BDD100K | CDDMSL | MAP | 27.1 | #1 of 1 | Archive leaderboard | report |
| Object Detection | Cityscapes to Foggy Cityscapes | CDDMSL | mAP | 54.3 | #1 of 1 | Archive leaderboard | report |
| Object Detection | Clipart1k | CDDMSL | MAP | 39.8 | #1 of 1 | Archive leaderboard | report |
| Object Detection | Comic2k | CDDMSL | mAP | 45.9 | #1 of 1 | Archive leaderboard | report |
| Object Detection | PASCAL VOC to Comic2k | CDDMSL | mAP | 46.3 | #2 of 2 | Archive leaderboard | report |
| Object Detection | PASCAL VOC to Watercolor2k | CDDMSL | mAp | 49.7 | #2 of 2 | Archive leaderboard | report |
| Object Detection | Pascal VOC to Clipart1K | CDDMSL | mAP | 40.4 | #3 of 3 | Archive leaderboard | report |
| Object Detection | Watercolor2k | CDDMSL | MAP | 49.8 | #1 of 1 | 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