ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers

• URL: http://arxiv.org/abs/2609.17152v1
• Date: Tue, 15 Sep 2026 13:17:30 GMT
• Title: ResLRP: The Role of Residual Cancellation in Attribution Instability in Vision Transformers
• Abstract summary: We show that the missing ingredient is the treatment of residual connections.<n>We introduce Residual-aware Layer-wise Relevance Propagation (ResLRP)<n>ResLRP is a simple extension of LRP whose propagation rules explicitly account for cancellations in residual branches.
• Score: 58.411900827911346
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Vision Transformers (ViTs) are central to most modern vision models, yet obtaining input attributions that are fine-grained, faithful, and stable remains challenging. Layer-wise Relevance Propagation (LRP) has been adapted to transformer attention, but in ViTs it often produces noisy, unfaithful explanations. We show that the missing ingredient is the treatment of residual connections: cancellation effects in residual pathways lead to attribution explosion. Moreover, we find that these cancellations are substantially stronger in ViTs than in language transformers. To address this issue, we introduce Residual-aware Layer-wise Relevance Propagation (ResLRP), a simple extension of LRP whose propagation rules explicitly account for cancellations in residual branches, are exactly conservative, and provably bound relevance explosion. Causal channel-wise interventions confirm that residual cancellation, not a generic regularization effect, drives the instability. ResLRP substantially improves attribution quality across faithfulness and localization, evaluated on ViT architectures spanning supervised, self-supervised, contrastive, hierarchical, and multimodal families, as well as on the ground-truth-controlled FunnyBirds benchmark. The largest gains arise in modern Vision Language Models (VLMs), with +27-29% localization and up to 3.4x faithfulness scores. Beyond benchmarks, ResLRP localizes Sparse Autoencoder (SAE) features in input space, and our residual amplification measure serves as an architecture-level diagnostic predicting where attribution degrades.

Related papers

• ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning [74.19730275669227]
  ARISE-RL is a novel full-cycle self-evolution framework for training open-ended agents.<n>We present Reward-Gated Self-Evolution Distillation (RG-SED), which distills a memory-augmented variant of the same policy back into itself.<n>We also present ECR-Bench, an expert-calibrated rubric benchmark suite covering single-tool deep research and multi-tool travel planning.
  arXiv  Detail & Related papers  (2026-09-01T10:54:13Z)
• TTSD-FAR: Test-Time Self-Distillation with Fisher-Anchored Restoration for Missing-Modality Emotion Recognition in LVLMs [83.78708832901194]
  Large video-language models (LVLMs) have shown remarkable performance on multimodal tasks like multimodal emotion recognition (ER) in the wild.<n>However, real-world deployment remains challenging: modalities may be missing or noisy at test time.<n>We propose a solution in which a frozen teacher guides an adaptive low-rank student via self-distillation.<n>Experiments on MELD, DFEW, and BAH under 0%-50% missing modalities show that this unified adaptation-restoration design consistently outperforms entropy-based adaptation, RAG, and perplexity-based generation.
  arXiv  Detail & Related papers  (2026-08-18T23:40:28Z)
• Actionable Hallucination Detection: Translating Latent Uncertainty into Agentic Critique [1.1172382217477128]
  Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures.<n>Existing detection methods fail to provide actionable, real-time correction as they either do not localize the hallucinations, or incur prohibitive inference latency.<n>We introduce the Latent Critic, a lightweight low-rank adapter (LoRA) that operates concurrently with a frozen base LLM's generation.
  arXiv  Detail & Related papers  (2026-08-11T03:26:16Z)
• Diagnosing and Mitigating Compounding Failures in Agentic Persuasion via Taxonomic Strategy Retrieval [2.5607169168631696]
  Taxonomic Strategy RAG (TS-RAG) is a systems intervention that routes strategies through a discrete categorical bottleneck to decouple argumentative structure from topical content.<n>TS-RAG significantly improves the transfer of abstract logic where standard semantic retrieval collapses.<n>It acts as a "capability bridge" in asymmetric deployments, empowering lightweight persuaders to consistently defeat superior opponents.
  arXiv  Detail & Related papers  (2026-06-23T12:16:27Z)
• Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation [50.139984798361375]
  We propose a training-free framework that removes redundancy via latent discrepancy.<n> LD-Pruning substantially reduces inference while maintaining high generation quality, achieving up to 2.35x speedup on Infinity-8B.
  arXiv  Detail & Related papers  (2026-05-29T19:34:39Z)
• Robustness of Transformer-Based Fluence Map Prediction Under Clinically Realistic Perturbations [4.066732323672965]
  We study a two-stage transformer pipeline that maps anatomy (CT and contours) to dose and then to beamlet fluence maps.<n>We compare fluence-stage transformer backbones with hierarchical, global, and hybrid attention, trained with a physics-informed loss enforcing energy consistency.<n>Results show smooth degradation under moderate perturbations but sharp failures under severe rotations and noise.
  arXiv  Detail & Related papers  (2026-04-28T21:32:47Z)
• Causal Bootstrapped Alignment for Unsupervised Video-Based Visible-Infrared Person Re-Identification [52.784239635604735]
  VVI-ReID is a critical technique for all-day surveillance, where temporal information provides additional cues beyond static images.<n>Existing approaches rely heavily on fully supervised learning with expensive cross-modality annotations, limiting scalability.<n>We propose a Causal Bootstrapped Alignment framework that explicitly exploits inherent video priors.
  arXiv  Detail & Related papers  (2026-04-17T02:15:59Z)
• Revisiting LRP: Positional Attribution as the Missing Ingredient for Transformer Explainability [53.21677928601684]
  Layer-wise relevance propagation is one of the most promising approaches to explainability in deep learning.<n>We propose specialized theoretically-grounded LRP rules designed to propagate attributions across various positional encoding methods.<n>Our method significantly outperforms the state-of-the-art in both vision and NLP explainability tasks.
  arXiv  Detail & Related papers  (2025-06-02T18:07:55Z)

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.