# Deep Interleaved Network for Image Super-Resolution With Asymmetric Co-Attention

arXiv: https://arxiv.org/abs/2004.11814 · HTML: https://mlsanity.com/paper/2004.11814/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Apr 2020.

## Built on by (most cited first, 7 of 7)

- [PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators](https://mlsanity.com/paper/2306.08918/) (2023)
- [CIR-Net: Cross-modality Interaction and Refinement for RGB-D Salient Object Detection](https://mlsanity.com/paper/2210.02843/) (2022)
- [Does Thermal Really Always Matter for RGB-T Salient Object Detection?](https://mlsanity.com/paper/2210.04266/) (2022)
- [A Weakly Supervised Learning Framework for Salient Object Detection via Hybrid Labels](https://mlsanity.com/paper/2209.02957/) (2022)
- [BCS-Net: Boundary, Context and Semantic for Automatic COVID-19 Lung Infection Segmentation from CT Images](https://mlsanity.com/paper/2207.08114/) (2022)
- [PSNet: Parallel Symmetric Network for Video Salient Object Detection](https://mlsanity.com/paper/2210.05912/) (2022)
- [Boundary Guided Semantic Learning for Real-time COVID-19 Lung Infection Segmentation System](https://mlsanity.com/paper/2209.02934/) (2022)

## Abstract (arXiv)

Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature. However, these methods are implemented as single-path stream to enrich feature maps from the input for the final prediction, which fail to fully incorporate former low-level features into later high-level features. In this paper, to tackle this problem, we propose a deep interleaved network (DIN) to learn how information at different states should be combined for image SR where shallow information guides deep representative features prediction. Our DIN follows a multi-branch pattern allowing multiple interconnected branches to interleave and fuse at different states. Besides, the asymmetric co-attention (AsyCA) is proposed and attacked to the interleaved nodes to adaptively emphasize informative features from different states and improve the discriminative ability of networks. Extensive experiments demonstrate the superiority of our proposed DIN in comparison with the state-of-the-art SR methods.