Texture segmentation stresses foundation segmentation because meaningful regions are defined by material or repeated appearance rather than object identity. Segment Anything Models (SAMs) often fail by default on such texture-defined partitions, but this failure is ambiguous: the texture evidence may be absent, missing from the proposal bank, or present but selected or assembled incorrectly by an object-centric readout. We investigate what texture-relevant evidence is preserved in frozen SAM before adaptation. We study two frozen evidence spaces: multiscale features probed with a minimal clustering readout, and the automatic proposal bank treated as evidence for a supervised consolidation readout. SAM remains frozen throughout; we do not fine-tune the backbone or retrain the proposal generator. Across RWTD, STLD, an ADE20K-selected refined-crop complement, and a ControlNet-stitched PTD bridge archive, frozen SAM is not a texture segmenter by default, but its failures are not simply due to texture blindness. Coarse frozen features preserve texture organization, and proposal banks often contain texture-aligned masks or fragments. Natural scenes more often require assembly and commitment over fragments, while cleaner synthetic cases tend to reduce to selecting an already coherent proposal. Default mask failure should therefore be decomposed into representation evidence, proposal-bank support, readout mismatch, and commitment failure.
Blogger's Review: This study provides an in-depth analysis of SAM's shortcomings in texture segmentation, proposing a perspective that combines texture evidence with the proposal bank. It reveals the complexity of feature extraction and readout processes within the model, offering significant insights for future optimizations, especially in diverse scene applications.