cs.CVNov 8, 2026

Dropping Tokens Without Dropping Them: Causal Attribution for Diabetic Retinopathy

Authors: Pramath Girish Haritz, Chandra Sekhar Seelamantula

Organizations: Indian Institute of Science

Abstract

In this work, we investigate whether attention-based attribution maps in a vision transformer provide causal explanations for diabetic retinopathy (DR) classification. We introduce a principled decomposition of attention into two attribution maps: the contribution (ctc_t), which satisfies the completeness axiom in explainable artificial intelligence (xAI), and the pull (ptp_t), which quantifies causal explanations. We define an identity relating ctc_t and ptp_t that characterizes when ctc_t fails to capture causality. We test whether each map is causally faithful on the MAPLES-DR dataset by dropping/inserting tokens, and report Necessity (NN), Sufficiency (SuSu), and Faithfulness Correlation (FCFC). The pull ptp_t achieves the highest causal alignment (FC=0.53FC = 0.53, N=0.71%N = 0.71\%, Su=3.0%Su = 3.0\%), outperforming Attention Rollout, Grad-CAM, and AttnLRP. Occlusion retains better sufficiency (Su=1.6%Su = 1.6\%) but is about 800 times slower. Furthermore, on MAPLES-DR, ptp_t achieves 70%70\% of the average precision (AP) of HRDecoder, a state-of-the-art supervised lesion segmentation model, despite the absence of pixel-level supervision. Together, these findings show that the pull ptp_t and the contribution ctc_t form computationally efficient attribution maps for reliable causal interpretation in safety-critical medical diagnostics. The code and demo are available at https://github.com/pramath-haritz/dr-xai.

Figures & tables

Explore similar work

CardsList
  1. Explainable Diabetic Retinopathy Classification Using Vision Foundation Models

    Aug 28, 2026Abhishek Verma, Anila Krishna, Abhishek Gajanan Bankar +1Retinal Disease ClassificationMedical Image Classification

  2. From Pixels to Explanations: Interpretable Diabetic Retinopathy Grading with CNN-Transformer Ensembles, Visual Explainability and Vision-Language Models

    Apr 25, 2026Pir Bakhsh Khokhar, Carmine Gravino, Fabio Palomba +2Diabetic Retinopathy GradingDeep Ensembles

  3. Causal-RetiGraph: Cross-Cohort Retinal Support and Same-Subject Pathway Analysis for Diabetic Retinopathy

    Jul 6, 2026Inam Ullah, Imran Razzak, Shoaib JameelCausal Mediation AnalysisDiabetic Retinopathy Grading