Spatial Information Bottleneck for Interpretable Visual Recognition

arXiv:2511.09239 · cs.CV · Submitted 2025-11-12 · Read on arXiv

cs.CV

Submitted: 2025-11-12

Updated: 2026-09-24

Terminology

• Information Bottleneck — 12× in this paper
• Interpretability — 11× in this paper · explained in 15 episodes
• Accuracy — 10× in this paper · explained in 1 episode
• Robustness — 8× in this paper · explained in 5 episodes
• Benchmark — 5× in this paper · explained in 2 episodes
• Decode — 4× in this paper · explained in 2 episodes
• Transformer — 4× in this paper · explained in 2 episodes
• Vector-Jacobian Products — 4× in this paper
• Mask Generation — 3× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Explainability — 2× in this paper · explained in 3 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Feature Selection — 1× in this paper · explained in 4 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Information-Theoretic Framework — 1× in this paper · explained in 2 episodes
• Loss Function — 1× in this paper · explained in 2 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Theoretical Guarantees — 1× in this paper · explained in 2 episodes

Sources

• Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
• Deep Variational Information Bottleneck
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• The information bottleneck method
• Post-hoc Concept Bottleneck Models
• Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations
• Label-Free Concept Bottleneck Models
• Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• SmoothGrad: removing noise by adding noise
• Striving for Simplicity: The All Convolutional Net

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models