cs.CVNov 8, 2026

ADC-RANet: Improving Resolution Adaptive Neural Networks with Attention, Distillation and Calibration

Authors: Jeferson Severino de Araujo, Lilian Hollard, Eric Granger, Marco Pedersoli

Organizations: LIVIA, Department of Systems Engineering, ETS Montreal, Canada

Abstract

Dynamic neural networks are a class of adaptive models in which the computation assigned to each input sample is determined dynamically, potentially reducing computational cost while maintaining similar performance. For image classification, the Resolution Adaptive Network (RANet) is a strong approach that progressively allocates computational resources across input scales based on sample difficulty. In this work, we introduce RANet with Attention, Distillation and Calibration (ADC-RANet), an enhanced version of RANet that improves performance across all computational budgets. Our approach combines three tightly connected components: bottom-up channel attention, top-down cascaded knowledge distillation, and overconfidence correction using MixUp, in a synergistic design that coordinates both pathways. Experiments on CIFAR-100 and ImageNet datasets show consistent gains while preserving the efficiency of RANet. Our code is available: https://github.com/jefersonseverino/ADC-RANet

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. DyRA: Portable Dynamic Resolution Adjustment Network for Existing Detectors

    Nov 28, 2023Daeun Seo, Hoeseok Yang, Hyungshin KimObject DetectionEfficient Object Detection

  2. ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling

    Feb 9, 2026Yilang Zhang, Bingcong Li, Niao He +1Residual LearningNeural Network Optimization

  3. RAViT: Resolution-Adaptive Vision Transformer

    Feb 27, 2026Martial Guidez, Stefan Duffner, Christophe GarciaEfficient ViTsVision Transformer