← 研踪 PaperTrailarXiv:2611.18861 · v2
Guided Group Featurizers (GGF): Improving Block-Sparse Featurizers with Object-Guided Learning
首次提交 2026-11-14 03:10
版本更新 2026-11-17 10:04
雷达观测 2026-11-18 19:43
摘要
Block-sparse featurizers (BSFs) use groups of learned directions to capture the multidimensional structure of visual concepts. However, grouping alone does not ensure that information about a concept is consolidated within a single group. We introduce Guided Group Featurizers (GGF), a novel object-guided extension that uses object annotations for initialization and training while preserving the BSF architecture. We assess whether each group's strongest response regions share an object type, part or material across images. Blinded GPT reviews give GGF groups an average semantic coherence score of %, versus % for SLiCS and % for supervised Vanilla BSF. GGF also leads in a separate blinded Gemini review. GGF's consolidation advantage extends to unguided categories: one selected group per category covers % of target-containing crops, versus % for supervised Vanilla BSF, at approximately 5% false-positive rates for both. Across COCO and VOC, GGF also improves single-group object Capture and localization over Vanilla BSFs, SLiCS and Concept-SAE. Its groups produce more focused and reproducible object responses while supporting recognition and retaining associations under rotation, scale and brightness changes. GGF also uses fewer learned parameters than Concept-SAE and shorter recorded VOC training loops than both supervised alternatives. These findings support object guidance for organizing more interpretable BSF groups and show that response concentration extends to categories excluded from guidance.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-17 10:04 · 最新观测版本
Guided Group Featurizers (GGF): Improving Block-Sparse Featurizers with Object-Guided Learning
Block-sparse featurizers (BSFs) use groups of learned directions to capture the multidimensional structure of visual concepts. However, grouping alone does not ensure that information about a concept is consolidated within a single group. We introduce Guided Group Featurizers (GGF), a novel object-guided extension that uses object annotations for initialization and training while preserving the BSF architecture. We assess whether each group's strongest response regions share an object type, part or material across images. Blinded GPT reviews give GGF groups an average semantic coherence score of %, versus % for SLiCS and % for supervised Vanilla BSF. GGF also leads in a separate blinded Gemini review. GGF's consolidation advantage extends to unguided categories: one selected group per category covers % of target-containing crops, versus % for supervised Vanilla BSF, at approximately 5% false-positive rates for both. Across COCO and VOC, GGF also improves single-group object Capture and localization over Vanilla BSFs, SLiCS and Concept-SAE. Its groups produce more focused and reproducible object responses while supporting recognition and retaining associations under rotation, scale and brightness changes. GGF also uses fewer learned parameters than Concept-SAE and shorter recorded VOC training loops than both supervised alternatives. These findings support object guidance for organizing more interpretable BSF groups and show that response concentration extends to categories excluded from guidance.
查看此版本解读 →查看此版本原文 ↗