# Dual Directed Capsule Network for Very Low Resolution Image Recognition

arXiv: https://arxiv.org/abs/1908.10027 · HTML: https://mlsanity.com/paper/1908.10027/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2019.

## Built on by (most cited first, 20 of 20)

- [Learning to Resize Images for Computer Vision Tasks](https://mlsanity.com/paper/2103.09950/) (2021)
- [RECLIP: Resource-efficient CLIP by Training with Small Images](https://mlsanity.com/paper/2304.06028/) (2023)
- [Distilling EEG Representations via Capsules for Affective Computing](https://mlsanity.com/paper/2105.00104/) (2021)
- [HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network](https://mlsanity.com/paper/2203.10699/) (2022)
- [Joint Learning of Blind Super-Resolution and Crack Segmentation for Realistic Degraded Images](https://mlsanity.com/paper/2302.12491/) (2023)
- [Hierarchical Deep CNN Feature Set-Based Representation Learning for Robust Cross-Resolution Face Recognition](https://mlsanity.com/paper/2103.13851/) (2021)
- [ARoFace: Alignment Robustness to Improve Low-Quality Face Recognition](https://mlsanity.com/paper/2407.14972/) (2024)
- [Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition](https://mlsanity.com/paper/2409.05384/) (2024)
- [Performance Evaluation of Action Recognition Models on Low Quality Videos](https://mlsanity.com/paper/2204.09166/) (2022)
- [Unsupervised Variational Translator for Bridging Image Restoration and High-Level Vision Tasks](https://mlsanity.com/paper/2408.08149/) (2024)
- [Low-Resolution Object Recognition with Cross-Resolution Relational Contrastive Distillation](https://mlsanity.com/paper/2409.02555/) (2024)
- [FriendNet: Detection-Friendly Dehazing Network](https://mlsanity.com/paper/2403.04443/) (2024)
- [Boosting Unconstrained Face Recognition with Targeted Style Adversary](https://mlsanity.com/paper/2408.07642/) (2024)
- [DArFace: Deformation Aware Robustness for Low Quality Face Recognition](https://mlsanity.com/paper/2505.08423/) (2025)
- [Iso-CapsNet: Isomorphic Capsule Network for Brain Graph Representation Learning](https://mlsanity.com/paper/2206.13465/) (2022)
- [Single Image Super-Resolution Based on Capsule Neural Networks](https://mlsanity.com/paper/2210.03743/) (2022)
- [SRMAE: Masked Image Modeling for Scale-Invariant Deep Representations](https://mlsanity.com/paper/2308.08884/) (2023)
- [Learning Unified Representations for Multi-Resolution Face Recognition](https://mlsanity.com/paper/2310.09563/) (2023)
- [Low-Resolution Face Recognition via Adaptable Instance-Relation Distillation](https://mlsanity.com/paper/2409.02049/) (2024)
- [Distilling Generative-Discriminative Representations for Very Low-Resolution Face Recognition](https://mlsanity.com/paper/2409.06371/) (2024)

## Abstract (arXiv)

Very low resolution (VLR) image recognition corresponds to classifying images with resolution 16x16 or less. Though it has widespread applicability when objects are captured at a very large stand-off distance (e.g. surveillance scenario) or from wide angle mobile cameras, it has received limited attention. This research presents a novel Dual Directed Capsule Network model, termed as DirectCapsNet, for addressing VLR digit and face recognition. The proposed architecture utilizes a combination of capsule and convolutional layers for learning an effective VLR recognition model. The architecture also incorporates two novel loss functions: (i) the proposed HR-anchor loss and (ii) the proposed targeted reconstruction loss, in order to overcome the challenges of limited information content in VLR images. The proposed losses use high resolution images as auxiliary data during training to "direct" discriminative feature learning. Multiple experiments for VLR digit classification and VLR face recognition are performed along with comparisons with state-of-the-art algorithms. The proposed DirectCapsNet consistently showcases state-of-the-art results; for example, on the UCCS face database, it shows over 95% face recognition accuracy when 16x16 images are matched with 80x80 images.