GeoReVis improves remote sensing image segmentation by combining mask revisions
GeoReVis: Learning Selective Revision and Evidence Consolidation for Remote Sensing Segmentation
Computer Vision and Pattern Recognition
Summary
Segmenting images from satellites or drones can be tricky because shapes and regions can be unclear or overlapping. The paper finds that trying to fix mistakes by revising segmentation masks can actually cause new errors or lose correct parts. The authors created GeoReVis, a method that carefully chooses better masks and combines pieces from multiple tries to keep all correct information together. This approach helps get more accurate segmentations by learning from past corrections and mixing evidence from different attempts.
What this means in practice
- •For geospatial analysts: Generate more accurate land use and object segmentation maps from satellite images by consolidating partial evidences across revisions.
- •For autonomous drone operators: Improve drone navigation and monitoring by refining image segmentations to reduce errors from flawed mask corrections.
Authors
Ke An, Liang Chen, Yupei Wang
Abstract
Recent methods try to inspect and revise masks to mitigate referential ambiguity and localization errors caused by complex spatial relations in language-guided remote sensing segmentation. However, these solutions often lead to Revision Degradation: revising missing regions may introduce errors into previously correct ones. Even a globally better mask can omit correct regions found in inferior masks. We term this Evidence Fragmentation: correct target evidence is scattered across imperfect masks. All masks generated by the model at this time are suboptimal. We propose GeoReVis, which unifies revision guided by execution feedback, Candidate Selection, and Cross-Mask Evidence Consolidation. It learns fine-grained revision from real actions that improve segmentation when executed and learns to select a better mask through quality comparisons between actual candidates, reducing the risk of degradation during revision. The selected whole mask can still discard useful regions. GeoReVis therefore retains all candidates across rounds, partitions their spatial disagreements into composable regions, and jointly reconstructs regions conditioned on the full instruction and context. This makes complementary and fragmentary evidence reusable regardless of its source candidate's overall quality, yielding improved segmentation. We further build a data pipeline to generate fine-grained multi-round segmentation trajectories and derive supervision for revision actions, candidate selection, and region composition from the model's own outputs, extending training beyond whole-mask IoU supervision. We also propose ReVis-Eval, a benchmark protocol evaluating multi-round revision and cross-round evidence consolidation accuracy. Experiments on ReVis-Eval and 5 benchmarks for remote sensing reasoning and referring segmentation demonstrate the effectiveness of GeoReVis.