Impression Space from Deep Template Network

• URL: http://arxiv.org/abs/2007.05441v1
• Date: Fri, 10 Jul 2020 15:29:33 GMT
• Title: Impression Space from Deep Template Network
• Authors: Gongfan Fang, Xinchao Wang, Haofei Zhang, Jie Song, Mingli Song
• Abstract summary: We show that a trained convolutional neural network has the capability to "remember" its input images. We propose a framework to establish an emphImpression Space upon an off-the-shelf pretrained network.
• Score: 72.86001835304185
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It is an innate ability for humans to imagine something only according to their impression, without having to memorize all the details of what they have seen. In this work, we would like to demonstrate that a trained convolutional neural network also has the capability to "remember" its input images. To achieve this, we propose a simple but powerful framework to establish an {\emph{Impression Space}} upon an off-the-shelf pretrained network. This network is referred to as the {\emph{Template Network}} because its filters will be used as templates to reconstruct images from the impression. In our framework, the impression space and image space are bridged by a layer-wise encoding and iterative decoding process. It turns out that the impression space indeed captures the salient features from images, and it can be directly applied to tasks such as unpaired image translation and image synthesis through impression matching without further network training. Furthermore, the impression naturally constructs a high-level common space for different data. Based on this, we propose a mechanism to model the data relations inside the impression space, which is able to reveal the feature similarity between images. Our code will be released.

Related papers

• Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence [88.00004819064672]
  Diffusion Hyperfeatures is a framework for consolidating multi-scale and multi-timestep feature maps into per-pixel feature descriptors. Our method achieves superior performance on the SPair-71k real image benchmark.
  arXiv  Detail & Related papers  (2023-05-23T17:58:05Z)
• A Deep Learning-based Compression and Classification Technique for Whole Slide Histopathology Images [0.31498833540989407]
  We build an ensemble of neural networks that enables a compressive autoencoder in a supervised fashion to retain a denser and more meaningful representation of the input histology images. We test the compressed images using transfer learning-based classifiers and show that they provide promising accuracy and classification performance.
  arXiv  Detail & Related papers  (2023-05-11T22:20:05Z)
• SparseFormer: Sparse Visual Recognition via Limited Latent Tokens [30.494412497158237]
  We present a new method, coined SparseFormer, to imitate human's sparse visual recognition in an end-to-end manner. SparseFormer circumvents most of dense operations on the image space and has much lower computational costs. Experiments on the ImageNet classification benchmark dataset show that SparseFormer achieves performance on par with canonical or well-established models.
  arXiv  Detail & Related papers  (2023-04-07T17:59:58Z)
• Sketch-Guided Text-to-Image Diffusion Models [57.12095262189362]
  We introduce a universal approach to guide a pretrained text-to-image diffusion model. Our method does not require to train a dedicated model or a specialized encoder for the task. We take a particular focus on the sketch-to-image translation task, revealing a robust and expressive way to generate images.
  arXiv  Detail & Related papers  (2022-11-24T18:45:32Z)
• Spiking sampling network for image sparse representation and dynamic vision sensor data compression [0.0]
  Sparse representation has attracted great attention because it can greatly save storage re- sources and find representative features of data in a low-dimensional space. In this paper, we propose a spiking sampling network. This network is composed of spiking neurons, and it can dynamically decide which pixel points should be retained and which ones need to be masked according to the input.
  arXiv  Detail & Related papers  (2022-11-08T11:11:10Z)
• Free-Form Image Inpainting via Contrastive Attention Network [64.05544199212831]
  In image inpainting tasks, masks with any shapes can appear anywhere in images which form complex patterns. It is difficult for encoders to capture such powerful representations under this complex situation. We propose a self-supervised Siamese inference network to improve the robustness and generalization.
  arXiv  Detail & Related papers  (2020-10-29T14:46:05Z)
• Pyramid Attention Networks for Image Restoration [124.34970277136061]
  Self-similarity refers to the image prior widely used in image restoration algorithms. Recent advanced deep convolutional neural network based methods for image restoration do not take full advantage of self-similarities. We present a novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid.
  arXiv  Detail & Related papers  (2020-04-28T21:12:36Z)
• Learning Representations by Predicting Bags of Visual Words [55.332200948110895]
  Self-supervised representation learning targets to learn convnet-based image representations from unlabeled data. Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially dense image descriptions.
  arXiv  Detail & Related papers  (2020-02-27T16:45:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.