cs.CVNov 13, 2026

Guided Group Featurizers (GGF): Improving Block-Sparse Featurizers with Object-Guided Learning

Authors: Waldemar Chang, Andrii Krutsylo

Organizations: Algoverse AI Research

Abstract

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 93.4±1.693.4\pm1.6%, versus 83.4±2.583.4\pm2.5% for SLiCS and 67.9±3.167.9\pm3.1% 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 66.1±1.966.1\pm1.9% of target-containing crops, versus 59.2±1.859.2\pm1.8% 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.

Figures & tables

Appendix figures & tables59 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. A Deeper Analysis of Block-Sparse Featurizers

    Aug 27, 2026Alexandru-Iulius Jerpelea, Amith AnanthramSparse AutoencodersRepresentation Disentanglement

  2. Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds

    Jun 23, 2026Thomas Fel, Matthew Kowal, Mozes Jacobs +22Neural Representation GeometryActivation Sparsity

  3. OrthoRF: Exploring Orthogonality in Object-Centric Representations

    Oct 26, 2026Despoina Touska, Bastiaan Onne Fagginger Auer, Alexandru Onose +6Object-Centric Representation LearningUnsupervised Visual Concept Discovery