Contrastive Feature Loss for Image Prediction

• URL: http://arxiv.org/abs/2111.06934v1
• Date: Fri, 12 Nov 2021 20:39:52 GMT
• Title: Contrastive Feature Loss for Image Prediction
• Authors: Alex Andonian, Taesung Park, Bryan Russell, Phillip Isola, Jun-Yan Zhu, Richard Zhang
• Abstract summary: Training supervised image synthesis models requires a critic to compare two images: the ground truth to the result. We introduce an information theory based approach to measuring similarity between two images. We show that our formulation boosts the perceptual realism of output images when used as a drop-in replacement for the L1 loss.
• Score: 55.373404869092866
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Training supervised image synthesis models requires a critic to compare two images: the ground truth to the result. Yet, this basic functionality remains an open problem. A popular line of approaches uses the L1 (mean absolute error) loss, either in the pixel or the feature space of pretrained deep networks. However, we observe that these losses tend to produce overly blurry and grey images, and other techniques such as GANs need to be employed to fight these artifacts. In this work, we introduce an information theory based approach to measuring similarity between two images. We argue that a good reconstruction should have high mutual information with the ground truth. This view enables learning a lightweight critic to "calibrate" a feature space in a contrastive manner, such that reconstructions of corresponding spatial patches are brought together, while other patches are repulsed. We show that our formulation immediately boosts the perceptual realism of output images when used as a drop-in replacement for the L1 loss, with or without an additional GAN loss.

Related papers

• Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised Learning [27.91000553525992]
  Self-supervised learning enables networks to learn discriminative features from massive data itself. We analyze the relation between similarity loss and feature-level cross-entropy loss. We provide theoretical analyses and experiments to show that a suitable combination of these two losses can get state-of-the-art results.
  arXiv  Detail & Related papers  (2023-01-08T13:30:39Z)
• CbwLoss: Constrained Bidirectional Weighted Loss for Self-supervised Learning of Depth and Pose [13.581694284209885]
  Photometric differences are used to train neural networks for estimating depth and camera pose from unlabeled monocular videos. In this paper, we deal with moving objects and occlusions utilizing the difference of the flow fields and depth structure generated by affine transformation and view synthesis. We mitigate the effect of textureless regions on model optimization by measuring differences between features with more semantic and contextual information without adding networks.
  arXiv  Detail & Related papers  (2022-12-12T12:18:24Z)
• When the Sun Goes Down: Repairing Photometric Losses for All-Day Depth Estimation [47.617222712429026]
  We show how to use a combination of three techniques to allow the existing photometric losses to work for both day and nighttime images. First, we introduce a per-pixel neural intensity transformation to compensate for the light changes that occur between successive frames. Second, we predict a per-pixel residual flow map that we use to correct the reprojection correspondences induced by the estimated ego-motion and depth.
  arXiv  Detail & Related papers  (2022-06-28T09:29:55Z)
• Invertible Network for Unpaired Low-light Image Enhancement [78.33382003460903]
  We propose to leverage the invertible network to enhance low-light image in forward process and degrade the normal-light one inversely with unpaired learning. In addition to the adversarial loss, we design various loss functions to ensure the stability of training and preserve more image details. We present a progressive self-guided enhancement process for low-light images and achieve favorable performance against the SOTAs.
  arXiv  Detail & Related papers  (2021-12-24T17:00:54Z)
• Contrastive Unpaired Translation using Focal Loss for Patch Classification [0.0]
  Contrastive Unpaired Translation is a new method for image-to-image translation. We show that using focal loss in place of cross-entropy loss within the PatchNCE loss can improve on the model's performance.
  arXiv  Detail & Related papers  (2021-09-25T20:22:33Z)
• Low-Light Image Enhancement with Normalizing Flow [92.52290821418778]
  In this paper, we investigate to model this one-to-many relationship via a proposed normalizing flow model. An invertible network that takes the low-light images/features as the condition and learns to map the distribution of normally exposed images into a Gaussian distribution. The experimental results on the existing benchmark datasets show our method achieves better quantitative and qualitative results, obtaining better-exposed illumination, less noise and artifact, and richer colors.
  arXiv  Detail & Related papers  (2021-09-13T12:45:08Z)
• The Spatially-Correlative Loss for Various Image Translation Tasks [69.62228639870114]
  We propose a novel spatially-correlative loss that is simple, efficient and yet effective for preserving scene structure consistency. Previous methods attempt this by using pixel-level cycle-consistency or feature-level matching losses. We show distinct improvement over baseline models in all three modes of unpaired I2I translation: single-modal, multi-modal, and even single-image translation.
  arXiv  Detail & Related papers  (2021-04-02T02:13:30Z)
• Image Restoration by Deep Projected GSURE [115.57142046076164]
  Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. We propose a new image restoration framework that is based on minimizing a loss function that includes a "projected-version" of the Generalized SteinUnbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN.
  arXiv  Detail & Related papers  (2021-02-04T08:52:46Z)
• A Loss Function for Generative Neural Networks Based on Watson's Perceptual Model [14.1081872409308]
  To train Variational Autoencoders (VAEs) to generate realistic imagery requires a loss function that reflects human perception of image similarity. We propose such a loss function based on Watson's perceptual model, which computes a weighted distance in frequency space and accounts for luminance and contrast masking. In experiments, VAEs trained with the new loss function generated realistic, high-quality image samples.
  arXiv  Detail & Related papers  (2020-06-26T15:36:11Z)
• Image Fine-grained Inpainting [89.17316318927621]
  We present a one-stage model that utilizes dense combinations of dilated convolutions to obtain larger and more effective receptive fields. To better train this efficient generator, except for frequently-used VGG feature matching loss, we design a novel self-guided regression loss. We also employ a discriminator with local and global branches to ensure local-global contents consistency.
  arXiv  Detail & Related papers  (2020-02-07T03:45:25Z)

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.