# Multi-Scale Dense Networks for Resource Efficient Image Classification

arXiv: https://arxiv.org/abs/1703.09844 · HTML: https://mlsanity.com/paper/1703.09844/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Mar 2017.

## Built on by (most cited first, 16 of 16)

- [Targeted Supervised Contrastive Learning for Long-Tailed Recognition](https://mlsanity.com/paper/2111.13998/) (2021)
- [LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision](https://mlsanity.com/paper/2112.09852/) (2021)
- [Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platforms](https://mlsanity.com/paper/2105.03596/) (2021)
- [A Survey of Neural Trees](https://mlsanity.com/paper/2209.03415/) (2022)
- [KTN: Knowledge Transfer Network for Learning Multi-person 2D-3D Correspondences](https://mlsanity.com/paper/2206.10090/) (2022)
- [Transformer-based Context Condensation for Boosting Feature Pyramids in Object Detection](https://mlsanity.com/paper/2207.06603/) (2022)
- [Layer Adaptive Deep Neural Networks for Out-of-distribution Detection](https://mlsanity.com/paper/2203.00192/) (2022)
- [ATHEENA: A Toolflow for Hardware Early-Exit Network Automation](https://mlsanity.com/paper/2304.08400/) (2023)
- [Energy-Aware Deep Learning on Resource-Constrained Hardware](https://mlsanity.com/paper/2505.12523/) (2025)
- [DynaMoE: Dynamic Token-Level Expert Activation with Layer-Wise Adaptive Capacity for Mixture-of-Experts Neural Networks](https://mlsanity.com/paper/2603.01697/) (2026)
- [EPEE: Towards Efficient and Effective Foundation Models in Biomedicine](https://mlsanity.com/paper/2503.02053/) (2025)
- [Auxiliary Loss Reweighting for Image Inpainting](https://mlsanity.com/paper/2111.07279/) (2021)
- [A State-of-the-art Survey of U-Net in Microscopic Image Analysis: from Simple Usage to Structure Mortification](https://mlsanity.com/paper/2202.06465/) (2022)
- [Enhancing Out-of-Distribution Detection with Multitesting-based Layer-wise Feature Fusion](https://mlsanity.com/paper/2403.10803/) (2024)
- [IMSAHLO: Integrating Multi-Scale Attention and Hybrid Loss Optimization Framework for Robust Neuronal Brain Cell Segmentation](https://mlsanity.com/paper/2601.11645/) (2026)
- [Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness](https://mlsanity.com/paper/2610.08560/) (2026)

## Abstract (arXiv)

In this paper we investigate image classification with computational resource limits at test time. Two such settings are: 1. anytime classification, where the network's prediction for a test example is progressively updated, facilitating the output of a prediction at any time; and 2. budgeted batch classification, where a fixed amount of computation is available to classify a set of examples that can be spent unevenly across "easier" and "harder" inputs. In contrast to most prior work, such as the popular Viola and Jones algorithm, our approach is based on convolutional neural networks. We train multiple classifiers with varying resource demands, which we adaptively apply during test time. To maximally re-use computation between the classifiers, we incorporate them as early-exits into a single deep convolutional neural network and inter-connect them with dense connectivity. To facilitate high quality classification early on, we use a two-dimensional multi-scale network architecture that maintains coarse and fine level features all-throughout the network. Experiments on three image-classification tasks demonstrate that our framework substantially improves the existing state-of-the-art in both settings.