cs.CVNov 14, 2026

Size-Matched Nulls Reveal What Block Ablation Measures in MambaVision

Authors: Tahmina Kousar, Tehseen Zia

Organizations: Department of Computer Science, COMSATS University Islamabad, Islamabad, Pakistan

Abstract

Hybrid vision backbones interleave Mamba state-space mixers with self-attention, and a block's role is usually probed by removing it and measuring the damage. We test what that measurement means in MambaVision. On all 50,000 ImageNet validation images and three model sizes, every block ablation is paired with a size-matched null, the same perturbation with its channels shuffled or their signs flipped. In top-1 accuracy and in true-class rank, real and null damage are nearly indistinguishable in absolute terms: pooled over the blocks of MambaVision-T, the content effect lies within [-0.044,+0.016] percentage points (90% interval). Two attention-only controls show that the test detects content, with real ablations worse than their nulls by up to 4.2 points in DeiT-Small and 1.0 point in Swin-T. Part of MambaVision's near-equivalence reflects how little damage its blocks do (0.11--0.34 points on average, against 1.7 and 2.1). Scaled by damage, its content share is comparable to Swin-T's in accuracy, lower in rank, and far below DeiT-Small's: single-block damage in MambaVision is small and mostly positional. Ablation also hides what blocks carry together: removing all blocks of one type compounds damage to 3.7--8.4 times the sum of single effects, far more than size-matched nulls, including nulls that keep the alignment between the blocks' perturbations; for adjacent pairs, aligned nulls reproduce most of it. Freezing input-dependent selection in all Mamba mixers shows that it accounts for 20--32% of the Mamba contribution, mainly through the B and C projections. We turn these results into a protocol for causal attribution in hybrid networks.

Figures & tables

Explore similar work

CardsList
  1. Norm or Direction? Decoding Vision Mambas for High-Resolution Vision

    Jul 21, 2026Jin Yu, Juyoun ParkVisual Representation LearningVisual SSMs

  2. Bridging Human and Model Attention: Explainability Analysis of CNN, Mamba, and ViT Architectures with Gaze-Based Validation

    Oct 8, 2026Marco Stefani, Edoardo Parpaiola, Matteo Bino +5Neural Network InterpretabilitySaliency Map Evaluation