# Where Does Texture Evidence Live in SAM? Features, Proposal Masks, and Texture Segmentation

arXiv: https://arxiv.org/abs/2606.14755 · HTML: https://mlsanity.com/paper/2606.14755/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Builds on (most cited first, 14 of 14)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Personalize Segment Anything Model with One Shot](https://mlsanity.com/paper/2305.03048/) (2023)
- [Material Recognition in the Wild with the Materials in Context Database](https://mlsanity.com/paper/1412.0623/) (2014)
- [AutoSAM: Adapting SAM to Medical Images by Overloading the Prompt Encoder](https://mlsanity.com/paper/2306.06370/) (2023)
- [From BoW to CNN: Two Decades of Texture Representation for Texture Classification](https://mlsanity.com/paper/1801.10324/) (2018)
- [Deep filter banks for texture recognition, description, and segmentation](https://mlsanity.com/paper/1507.02620/) (2015)
- [ASAM: Boosting Segment Anything Model with Adversarial Tuning](https://mlsanity.com/paper/2405.00256/) (2024)
- [TextureSAM: Towards a Texture Aware Foundation Model for Segmentation](https://mlsanity.com/paper/2505.16540/) (2025)
- [Texture segmentation with Fully Convolutional Networks](https://mlsanity.com/paper/1703.05230/) (2017)

## Abstract (arXiv)

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 ask what texture-relevant evidence is already 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 is 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 simple 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 more often 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.