Cover Image

Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bağcı, Doğukan, Schiele, Bernt, Schaub-Meyer, Simone, Fischer, Jonas, Hesse, Robin
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Disentangling Polysemantic Channels in Convolutional Neural Networks
by: Hesse, Robin, et al.
Published: (2025)

Beyond Accuracy: What Matters in Designing Well-Behaved Image Classification Models?
by: Hesse, Robin, et al.
Published: (2025)

What is Missing? Explaining Neurons Activated by Absent Concepts
by: Hesse, Robin, et al.
Published: (2026)

Benchmarking the Attribution Quality of Vision Models
by: Hesse, Robin, et al.
Published: (2024)

Optimising for Interpretability: Convolutional Dynamic Alignment Networks
by: Böhle, Moritz, et al.
Published: (2021)

Disentangling Polysemantic Neurons with a Null-Calibrated Polysemanticity Index and Causal Patch Interventions
by: Gupta, Manan, et al.
Published: (2025)

FaCT: Faithful Concept Traces for Explaining Neural Network Decisions
by: Parchami-Araghi, Amin, et al.
Published: (2025)

Towards Better Understanding Attribution Methods
by: Rao, Sukrut, et al.
Published: (2022)

B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
by: Arya, Shreyash, et al.
Published: (2024)

CFM: Language-aligned Concept Foundation Model for Vision
by: Wittenmayer, Kai, et al.
Published: (2026)

VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow
by: Gorgun, Ada, et al.
Published: (2025)

Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing
by: Anani, Alaa, et al.
Published: (2024)

GLASS: Guided Latent Slot Diffusion for Object-Centric Learning
by: Singh, Krishnakant, et al.
Published: (2024)

Evaluating Object-Centric Models beyond Object Discovery
by: Singh, Krishnakant, et al.
Published: (2026)

Better Understanding Differences in Attribution Methods via Systematic Evaluations
by: Rao, Sukrut, et al.
Published: (2023)

Adversarial Training against Location-Optimized Adversarial Patches
by: Rao, Sukrut, et al.
Published: (2020)

Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning
by: Pham, Nhi, et al.
Published: (2025)

Spatial Reasoners for Continuous Variables in Any Domain
by: Pogodzinski, Bart, et al.
Published: (2025)

Spatial Reasoning with Denoising Models
by: Wewer, Christopher, et al.
Published: (2025)

Test-Time Visual In-Context Tuning
by: Xie, Jiahao, et al.
Published: (2025)

Pixel-level Certified Explanations via Randomized Smoothing
by: Anani, Alaa, et al.
Published: (2025)

Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery
by: Rao, Sukrut, et al.
Published: (2024)

Activation Subspaces for Out-of-Distribution Detection
by: Zöngür, Barış, et al.
Published: (2025)

Are All Marine Species Created Equal? Performance Disparities in Underwater Object Detection
by: Wille, Melanie, et al.
Published: (2025)

Studying How to Efficiently and Effectively Guide Models with Explanations
by: Rao, Sukrut, et al.
Published: (2023)

Good Teachers Explain: Explanation-Enhanced Knowledge Distillation
by: Parchami-Araghi, Amin, et al.
Published: (2024)

Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions
by: Gorgun, Ada, et al.
Published: (2025)

ELODI: Ensemble Logit Difference Inhibition for Positive-Congruent Training
by: Zhao, Yue, et al.
Published: (2022)

AnyUp: Universal Feature Upsampling
by: Wimmer, Thomas, et al.
Published: (2025)

PURE: Turning Polysemantic Neurons Into Pure Features by Identifying Relevant Circuits
by: Dreyer, Maximilian, et al.
Published: (2024)

B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers
by: Böhle, Moritz, et al.
Published: (2023)

AIM: Amending Inherent Interpretability via Self-Supervised Masking
by: Alshami, Eyad, et al.
Published: (2025)

MEt3R: Measuring Multi-View Consistency in Generated Images
by: Asim, Mohammad, et al.
Published: (2025)

On the Robustness Tradeoff in Fine-Tuning
by: Li, Kunyang, et al.
Published: (2025)

PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language Understanding
by: Kuzucu, Selim, et al.
Published: (2026)

Certified Circuits: Stability Guarantees for Mechanistic Circuits
by: Anani, Alaa, et al.
Published: (2026)

DAVE: Distribution-aware Attribution via ViT Gradient Decomposition
by: Wróbel, Adam, et al.
Published: (2026)

An Embarrassingly Simple Baseline for Imbalanced Semi-Supervised Learning
by: Chen, Hao, et al.
Published: (2022)

MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying
by: Shi, Shaoshuai, et al.
Published: (2023)

Improved Segmentation of Polyps and Visual Explainability Analysis
by: Asare, Akwasi, et al.
Published: (2025)