Dissecting Image Crops
- URL: http://arxiv.org/abs/2011.11831v4
- Date: Sun, 5 Sep 2021 23:39:12 GMT
- Title: Dissecting Image Crops
- Authors: Basile Van Hoorick, Carl Vondrick
- Abstract summary: The elementary operation of cropping underpins nearly every computer vision system.
This paper investigates the subtle traces introduced by this operation.
We study how to detect these traces, and investigate the impact that cropping has on the image distribution.
- Score: 22.482090207522358
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The elementary operation of cropping underpins nearly every computer vision
system, ranging from data augmentation and translation invariance to
computational photography and representation learning. This paper investigates
the subtle traces introduced by this operation. For example, despite
refinements to camera optics, lenses will leave behind certain clues, notably
chromatic aberration and vignetting. Photographers also leave behind other
clues relating to image aesthetics and scene composition. We study how to
detect these traces, and investigate the impact that cropping has on the image
distribution. While our aim is to dissect the fundamental impact of spatial
crops, there are also a number of practical implications to our work, such as
revealing faulty photojournalism and equipping neural network researchers with
a better understanding of shortcut learning. Code is available at
https://github.com/basilevh/dissecting-image-crops.
Related papers
- Mark My Words: Dangers of Watermarked Images in ImageNet [0.0]
A significant number of images in the ImageNet dataset contain watermarks.
A variety of ImageNet classes, such as "monitor", "broom", "apron" and "safe" rely on spurious correlations.
We propose a simple approach to mitigate this issue in fine-tuned networks.
arXiv Detail & Related papers (2023-03-09T18:51:31Z) - Saliency Guided Contrastive Learning on Scene Images [71.07412958621052]
We leverage the saliency map derived from the model's output during learning to highlight discriminative regions and guide the whole contrastive learning.
Our method significantly improves the performance of self-supervised learning on scene images by +1.1, +4.3, +2.2 Top1 accuracy in ImageNet linear evaluation, Semi-supervised learning with 1% and 10% ImageNet labels, respectively.
arXiv Detail & Related papers (2023-02-22T15:54:07Z) - Hierarchical Semantic Segmentation using Psychometric Learning [17.417302703539367]
We develop a novel approach to collect segmentation annotations from experts based on psychometric testing.
Our method consists of the psychometric testing procedure, active query selection, query enhancement, and a deep metric learning model.
We show the merits of our method with evaluation on the synthetically generated image, aerial image and histology image.
arXiv Detail & Related papers (2021-07-07T13:38:33Z) - Computer-aided Interpretable Features for Leaf Image Classification [0.0]
We introduce 52 computationally efficient features to classify plant species.
Length, width, area, texture correlation, monotonicity and scagnostics are to name few of them.
The results show that the features are sufficient to discriminate the classes of interest under both supervised and unsupervised learning settings.
arXiv Detail & Related papers (2021-06-15T12:11:10Z) - Factors of Influence for Transfer Learning across Diverse Appearance
Domains and Task Types [50.1843146606122]
A simple form of transfer learning is common in current state-of-the-art computer vision models.
Previous systematic studies of transfer learning have been limited and the circumstances in which it is expected to work are not fully understood.
In this paper we carry out an extensive experimental exploration of transfer learning across vastly different image domains.
arXiv Detail & Related papers (2021-03-24T16:24:20Z) - Self-Adaptively Learning to Demoire from Focused and Defocused Image
Pairs [97.67638106818613]
Moire artifacts are common in digital photography, resulting from the interference between high-frequency scene content and the color filter array of the camera.
Existing deep learning-based demoireing methods trained on large scale iteration are limited in handling various complex moire patterns.
We propose a self-adaptive learning method for demoireing a high-frequency image, with the help of an additional defocused moire-free blur image.
arXiv Detail & Related papers (2020-11-03T23:09:02Z) - Improving Object Detection with Selective Self-supervised Self-training [62.792445237541145]
We study how to leverage Web images to augment human-curated object detection datasets.
We retrieve Web images by image-to-image search, which incurs less domain shift from the curated data than other search methods.
We propose a novel learning method motivated by two parallel lines of work that explore unlabeled data for image classification.
arXiv Detail & Related papers (2020-07-17T18:05:01Z) - Distilling Localization for Self-Supervised Representation Learning [82.79808902674282]
Contrastive learning has revolutionized unsupervised representation learning.
Current contrastive models are ineffective at localizing the foreground object.
We propose a data-driven approach for learning in variance to backgrounds.
arXiv Detail & Related papers (2020-04-14T16:29:42Z) - Self-Supervised Linear Motion Deblurring [112.75317069916579]
Deep convolutional neural networks are state-of-the-art for image deblurring.
We present a differentiable reblur model for self-supervised motion deblurring.
Our experiments demonstrate that self-supervised single image deblurring is really feasible.
arXiv Detail & Related papers (2020-02-10T20:15:21Z) - Learning Transformation-Aware Embeddings for Image Forensics [15.484408315588569]
Image Provenance Analysis aims at discovering relationships among different manipulated image versions that share content.
One of the main sub-problems for provenance analysis that has not yet been addressed directly is the edit ordering of images that share full content or are near-duplicates.
This paper introduces a novel deep learning-based approach to provide a plausible ordering to images that have been generated from a single image through transformations.
arXiv Detail & Related papers (2020-01-13T22:01:24Z)
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.