# Supervised Deep Learning for Content-Aware Image Retargeting with Fourier Convolutions

arXiv: https://arxiv.org/abs/2306.07383 · HTML: https://mlsanity.com/paper/2306.07383/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 12 Jun 2023.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Resolution-robust Large Mask Inpainting with Fourier Convolutions](https://mlsanity.com/paper/2109.07161/) (2021)
- [Which Training Methods for GANs do actually Converge?](https://mlsanity.com/paper/1801.04406/) (2018)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients](https://mlsanity.com/paper/1711.09404/) (2017)
- [Effective Aesthetics Prediction with Multi-level Spatially Pooled Features](https://mlsanity.com/paper/1904.01382/) (2019)
- [Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models](https://mlsanity.com/paper/2103.15545/) (2021)
- [Generating natural images with direct Patch Distributions Matching](https://mlsanity.com/paper/2203.11862/) (2022)
- [Weakly- and Self-Supervised Learning for Content-Aware Deep Image Retargeting](https://mlsanity.com/paper/1708.02731/) (2017)
- [Cycle-IR: Deep Cyclic Image Retargeting](https://mlsanity.com/paper/1905.03556/) (2019)
- [DCIL: Deep Contextual Internal Learning for Image Restoration and Image Retargeting](https://mlsanity.com/paper/1912.04229/) (2019)
- [DeepIR: A Deep Semantics Driven Framework for Image Retargeting](https://mlsanity.com/paper/1811.07793/) (2018)
- [Context-Aware Saliency Detection for Image Retargeting Using Convolutional Neural Networks](https://mlsanity.com/paper/1910.08071/) (2019)
- [Self-Play Reinforcement Learning for Fast Image Retargeting](https://mlsanity.com/paper/2010.00909/) (2020)
- [OAIR: Object-Aware Image Retargeting Using PSO and Aesthetic Quality Assessment](https://mlsanity.com/paper/2209.04804/) (2022)

## Abstract (arXiv)

Image retargeting aims to alter the size of the image with attention to the contents. One of the main obstacles to training deep learning models for image retargeting is the need for a vast labeled dataset. Labeled datasets are unavailable for training deep learning models in the image retargeting tasks. As a result, we present a new supervised approach for training deep learning models. We use the original images as ground truth and create inputs for the model by resizing and cropping the original images. A second challenge is generating different image sizes in inference time. However, regular convolutional neural networks cannot generate images of different sizes than the input image. To address this issue, we introduced a new method for supervised learning. In our approach, a mask is generated to show the desired size and location of the object. Then the mask and the input image are fed to the network. Comparing image retargeting methods and our proposed method demonstrates the model's ability to produce high-quality retargeted images. Afterward, we compute the image quality assessment score for each output image based on different techniques and illustrate the effectiveness of our approach.