Contrastive Mask Fidelity: Reference-Free Auditing of Ground-Truth Masks in Remote Sensing Semantic Segmentation

Segmentation is a fundamental vision task underlying numerous downstream applications. Recent promptable segmentation models, such as Segment Anything Model 3 (SAM3), extend segmentation from category-agnostic mask prediction to concept-guided localization conditioned on high-level textual prompts. However, existing benchmarks primarily evaluate mask accuracy or object presence, leaving unclear whether these models faithfully ground the queried concept or instead rely on visually salient but semantically misleading cues. We introduce CAFE: \textbf{C}ounterfactual \textbf{A}ttribute \textbf{F}actuality \textbf{E}valuation, a novel benchmark for evaluating concept-faithful segmentation in promptable segmentation models. Our \textbf{CAFE} is built on attribute-level counterfactual manipulation: the target region and ground-truth mask are preserved, while attributes such as surface appearance, context, or material composition are modified to introduce misleading semantic cues. The benchmark contains 2,146 paired test samples, each consisting of a target image, a ground-truth mask, a positive prompt, and a misleading negative prompt. These samples cover three counterfactual categories: Superficial Mimicry (\textbf{SM}), Context Conflict (\textbf{CC}), and Ontological Conflict (\textbf{OC}). We evaluate various model types and sizes on our CAFE. Experiments reveal a systematic gap between localization quality and concept discrimination: models often generate accurate masks even for misleading prompts, suggesting that strong mask prediction does not necessarily imply faithful semantic grounding. Our CAFE provides a controlled benchmark for diagnosing whether promptable segmentation models perform concept-faithful grounding rather than shortcut-driven mask retrieval.

Semantic segmentation in remote sensing requires costly pixel-level annotations, and nearly every problem demands a new dataset since models rarely transfer across sensors, platforms, or geographies. Existing human-in-the-loop frameworks expand sparse clicks into dense supervision via auxiliary machinery (pseudo-labels, propagation, CRFs, foundation-model prompts, auxiliary heads), all operating on the model's predictive distribution. A confidently wrong pixel is indistinguishable from a confidently correct one in that distribution by construction, so no rule reading it can separate the two; the distinguishing signal is external to the model. This paper hypothesizes that expert clicks targeting confident model errors, not arbitrary pixels, suffice to match dense supervision, with no expansion machinery. iSAGE (Iterative Sparse Annotation Guided by Expert) realizes this hypothesis on an integrated open-source platform, where an error-weighted loss amplifies the gradient at each click and the annotation record itself is the dataset, extensible, correctable, and auditable. Experiments use a minimum-effort regime: at most one labeled pixel per class per frame. On BsB Aerial, iSAGE recovers 97.2% of dense supervision (74.79% mIoU on 0.040% of pixels) with contrasting class dynamics: amorphous classes (permeable areas) saturate from the seed, while small classes (cars) require late-iteration effort. On ISPRS Vaihingen (external benchmark), iSAGE reaches 76.78% mIoU with 0.011% of pixels, matching the dense baseline (76.65%) and exceeding all published methods. Under the same pipeline, four output-reading mechanisms (oracle entropy across budgets 1--100x, pseudo-labels across thresholds 0.90--0.99, CRF-based propagation, uniform random) plateau 7.4 to 14.5 pp below iSAGE. Across 31 surveyed methods, iSAGE is the only iterative human-in-the-loop framework operating without auxiliary machinery.

Open-vocabulary remote sensing image segmentation (OVRSIS) remains underexplored due to fragmented datasets, limited training diversity, and the lack of evaluation benchmarks that reflect realistic geospatial application demands. Our previous \textit{OVRSISBenchV1} established an initial cross-dataset evaluation protocol, but its limited scope is insufficient for assessing realistic open-world generalization. To address this issue, we propose \textit{OVRSISBenchV2}, a large-scale and application-oriented benchmark for OVRSIS. We first construct \textbf{OVRSIS95K}, a balanced dataset of about 95K image--mask pairs covering 35 common semantic categories across diverse remote sensing scenes. Built upon OVRSIS95K and 10 downstream datasets, OVRSISBenchV2 contains 170K images and 128 categories, substantially expanding scene diversity, semantic coverage, and evaluation difficulty. Beyond standard open-vocabulary segmentation, it further includes downstream protocols for building extraction, road extraction, and flood detection, thereby better reflecting realistic geospatial application demands and complex deployment scenarios. We also propose \textbf{Pi-Seg}, a baseline for OVRSIS. Pi-Seg improves transferability through a \textbf{positive-incentive noise} mechanism, where learnable and semantically guided perturbations broaden the visual-text feature space during training. Extensive experiments on OVRSISBenchV1, OVRSISBenchV2, and downstream tasks show that Pi-Seg delivers strong and consistent results, particularly on the more challenging OVRSISBenchV2 benchmark. Our results highlight both the importance of realistic benchmark design and the effectiveness of perturbation-based transfer for OVRSIS. The code and datasets are available at \href{https://github.com/LiBingyu01/Pi-Seg}{LiBingyu01/Pi-Seg}.