TopoDPO: Dense Preference Alignment for Structure-Sensitive Aerial Referring Segmentation
Organizations: School of Information Science and Engineering, Lanzhou University, Lanzhou 730000, China. · School of Computing, National University of Singapore, Singapore 119077. · Huawei, Shenzhen 518129, China.
Abstract
Preference optimization for multimodal segmentation faces a granularity mismatch: dense masks contain spatially heterogeneous preference signals, whereas image-level objectives assign one shared nonlinear weight to all spatial margins. We introduce TopoDPO, a topology-aware dense preference alignment framework for structure-sensitive aerial referring segmentation. Topo-Prior mines informative preference pairs using connected-component discrepancy and macro-corner recall, while the dense objective applies the preference penalty to each local margin before spatial aggregation against a frozen supervised reference. On Topo-RS-Hard, a 4590-instance structural stress set, TopoDPO improves intersection over union (IoU) from 50.91% to 51.24% over image-level direct preference optimization (DPO) and reduces Betti-0 error from 1.34 to 0.90; paired image-cluster bootstrap intervals against image-level DPO exclude zero for all five reported metrics. Matched supervised controls and a complete factorial analysis separate the effects of topology-aware pair mining, localized correction, and dense reference-relative preference weighting. An unfiltered stratification over all 39,244 validation records further shows the clearest structural gains on samples with moderate or severe pre-alignment component-count errors. The code is publicly available at: https://github.com/phy709/TopoDPO.
Figures & tables
| Method | Alignment/loss | IoU | F1 | Precision | Corner recall | |
|---|---|---|---|---|---|---|
| SFT baseline (2025) [ 3 ] | BCE+Dice | 47.88 | 56.04 | 59.97 | 2.77 | 63.59 |
| SFT + clDice (2021) [ 10 ] | Topology loss | 48.57 | 56.76 | 60.54 | 2.37 | 64.51 |
| SFT + SCNP (2026) [ 21 ] | Local structural loss | 48.90 | 57.12 | 59.95 | 2.27 | 65.06 |
| Topo-Prior continued SFT (ours) | BCE+Dice | 49.63 | 57.92 | 60.08 | 2.12 | 65.38 |
| Topo-Prior masked BCE (ours) | Disagreement pixels | 50.72 | 59.03 | 60.18 | 1.18 | 67.21 |
| Vanilla DPO (2023) [ 7 ] | Image level | 50.91 | 59.16 | 59.62 | 1.34 | 67.58 |
| Baseline | Metric | Mean difference | 95% confidence interval |
|---|---|---|---|
| Vanilla DPO (2023) [ 7 ] | IoU | ||
| F1 | |||
| Precision | |||
| Corner recall | |||
| RN-DPO (2026) [ 16 ] | IoU |
| ID | Pair selection | Objective/configuration | IoU | F1 | Corner recall | |
|---|---|---|---|---|---|---|
| A1 | Random | Image-level DPO | 49.18 | 58.31 | 2.06 | 64.72 |
| A2 | Random | Pixel-level DPO | 49.52 | 58.78 | 1.85 | 65.12 |
| A3 | Topo-Prior | Image-level DPO | 50.91 | 59.16 | 1.34 | 67.58 |
| A4 | Topo-Prior | Pixel-level DPO | 51.24 | 59.45 | 0.90 | 67.83 |
| B1 | Topo-Prior | 48.93 | 58.85 | 1.55 | 65.87 | |
| B2 | Topo-Prior | 51.24 | 59.45 | 0.90 | 67.83 |
Referring Image Segmentation
Referring image segmentation maps a natural-language description of an object or region to its pixels in an image.
See all 50 papers