SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation

• URL: http://arxiv.org/abs/2604.25315v1
• Date: Tue, 28 Apr 2026 07:25:07 GMT
• Title: SaliencyDecor: Enhancing Neural Network Interpretability through Feature Decorrelation
• Abstract summary: SaliencyDecor is a training framework that enforces feature decorrelation to improve attribution fidelity without modifying saliency methods or model architectures.<n>We show that our method produces substantially sharper and more object-focused saliency maps while simultaneously improving predictive performance.
• Score: 4.096797783087454
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Gradient-based saliency methods are widely used to interpret deep neural networks, yet they often produce noisy and unstable explanations that poorly align with semantically meaningful input features. We argue that a fundamental cause of this behavior lies in the geometry of learned representations: correlated feature dimensions diffuse attribution gradients across redundant directions, resulting in blurred and unreliable saliency maps. To address this issue, we identify feature correlation as a structural limitation of gradient-based interpretability and propose SaliencyDecor, a training framework that enforces feature decorrelation to improve attribution fidelity without modifying saliency methods or model architectures by reshaping the feature space toward orthogonality, our approach promotes more concentrated gradient flow and improves the fidelity of saliency-based explanations. SaliencyDecor jointly optimizes classification, prediction consistency under feature masking, and a decorrelation regularizer, requiring no architectural changes or inference-time overhead. Extensive experiments across multiple benchmarks and architectures demonstrate that our method produces substantially sharper and more object-focused saliency maps while simultaneously improving predictive performance, achieving accuracy gains across the datasets. These results establish our method as a principled mechanism for enhancing both interpretability and accuracy, challenging the conventional trade-off between explanation quality and model performance.

Related papers

• Geometrical fairness in graph neural networks [0.5872014229110214]
  We introduce a fairness-aware adaptation of graph-based diffusion by modifying the underlying Laplacian operator.<n>We provide a principled analysis of the resulting behavior and establish theoretical insights into fairness properties.
  arXiv  Detail & Related papers  (2026-06-16T08:50:30Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Implicit Neural Representation-Based Continuous Single Image Super Resolution: An Empirical Study [50.15623093332659]
  Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR)<n>We compare existing techniques across diverse settings and present aggregated performance results on multiple image quality metrics.<n>We examine a new loss function that penalizes intensity variations while preserving edges, textures, and finer details during training.
  arXiv  Detail & Related papers  (2026-01-25T07:09:20Z)
• Semantic-guided Fine-tuning of Foundation Model for Long-tailed Visual Recognition [38.74388860692423]
  We propose a novel approach, Semantic-guided fine-tuning of foundation model for long-tailed visual recognition (Sage)<n>We introduce an SG-Adapter that integrates class descriptions as semantic guidance to guide the fine-tuning of the visual encoder.<n>Experiments on benchmark datasets demonstrate the effectiveness of the proposed Sage in enhancing performance in long-tailed learning.
  arXiv  Detail & Related papers  (2025-07-17T05:47:19Z)
• Flows and Diffusions on the Neural Manifold [0.0]
  Diffusion and flow-based generative models have achieved remarkable success in domains such as image synthesis, video generation, and natural language modeling.<n>In this work, we extend these advances to weight space learning by leveraging recent techniques to incorporate structural priors derived from optimization dynamics.<n>We unify several trajectory inference techniques towards matching a gradient flow, providing a theoretical framework for treating optimization paths as inductive bias.
  arXiv  Detail & Related papers  (2025-07-14T02:26:06Z)
• Structured Convergence in Large Language Model Representations via Hierarchical Latent Space Folding [0.0]
  Token representations in high-dimensional latent spaces often exhibit redundancy, limiting computational efficiency and reducing structural coherence across model layers.<n>This paper introduces a structured transformation mechanism that enforces a multi-scale organization within learned embeddings.<n> Empirical evaluation demonstrates a reduction in representational variance across layers, contributing to more stable perplexity distributions and enhancing predictive confidence in text generation.
  arXiv  Detail & Related papers  (2025-02-13T04:01:54Z)
• Contextually Entangled Gradient Mapping for Optimized LLM Comprehension [0.0]
  Entually Entangled Gradient Mapping (CEGM) introduces a new approach to gradient optimization.<n>It treats gradients as dynamic carriers of contextual dependencies rather than isolated numerical entities.<n>The proposed methodology bridges critical gaps in existing optimization strategies.
  arXiv  Detail & Related papers  (2025-01-28T11:50:35Z)
• Unlearning-based Neural Interpretations [51.99182464831169]
  We show that current baselines defined using static functions are biased, fragile and manipulable.<n>We propose UNI to compute an (un)learnable, debiased and adaptive baseline by perturbing the input towards an unlearning direction of steepest ascent.
  arXiv  Detail & Related papers  (2024-10-10T16:02:39Z)
• Improving Network Interpretability via Explanation Consistency Evaluation [56.14036428778861]
  We propose a framework that acquires more explainable activation heatmaps and simultaneously increase the model performance. Specifically, our framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning. Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations.
  arXiv  Detail & Related papers  (2024-08-08T17:20:08Z)
• Deep Equilibrium Assisted Block Sparse Coding of Inter-dependent Signals: Application to Hyperspectral Imaging [71.57324258813675]
  A dataset of inter-dependent signals is defined as a matrix whose columns demonstrate strong dependencies. A neural network is employed to act as structure prior and reveal the underlying signal interdependencies. Deep unrolling and Deep equilibrium based algorithms are developed, forming highly interpretable and concise deep-learning-based architectures.
  arXiv  Detail & Related papers  (2022-03-29T21:00:39Z)
• Rethinking Skip Connection with Layer Normalization in Transformers and ResNets [49.87919454950763]
  Skip connection is a widely-used technique to improve the performance of deep neural networks. In this work, we investigate how the scale factors in the effectiveness of the skip connection.
  arXiv  Detail & Related papers  (2021-05-15T11:44:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.