Learning Visual Representations for Transfer Learning by Suppressing Texture

• URL: http://arxiv.org/abs/2011.01901v2
• Date: Wed, 4 Nov 2020 16:41:17 GMT
• Title: Learning Visual Representations for Transfer Learning by Suppressing Texture
• Authors: Shlok Mishra, Anshul Shah, Ankan Bansal, Jonghyun Choi, Abhinav Shrivastava, Abhishek Sharma, David Jacobs
• Abstract summary: In self-supervised learning, texture as a low-level cue may provide shortcuts that prevent the network from learning higher level representations. We propose to use classic methods based on anisotropic diffusion to augment training using images with suppressed texture. We empirically show that our method achieves state-of-the-art results on object detection and image classification.
• Score: 38.901410057407766
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent literature has shown that features obtained from supervised training of CNNs may over-emphasize texture rather than encoding high-level information. In self-supervised learning in particular, texture as a low-level cue may provide shortcuts that prevent the network from learning higher level representations. To address these problems we propose to use classic methods based on anisotropic diffusion to augment training using images with suppressed texture. This simple method helps retain important edge information and suppress texture at the same time. We empirically show that our method achieves state-of-the-art results on object detection and image classification with eight diverse datasets in either supervised or self-supervised learning tasks such as MoCoV2 and Jigsaw. Our method is particularly effective for transfer learning tasks and we observed improved performance on five standard transfer learning datasets. The large improvements (up to 11.49\%) on the Sketch-ImageNet dataset, DTD dataset and additional visual analyses with saliency maps suggest that our approach helps in learning better representations that better transfer.

Related papers

• Free-ATM: Exploring Unsupervised Learning on Diffusion-Generated Images with Free Attention Masks [64.67735676127208]
  Text-to-image diffusion models have shown great potential for benefiting image recognition. Although promising, there has been inadequate exploration dedicated to unsupervised learning on diffusion-generated images. We introduce customized solutions by fully exploiting the aforementioned free attention masks.
  arXiv  Detail & Related papers  (2023-08-13T10:07:46Z)
• Hybrid BYOL-ViT: Efficient approach to deal with small Datasets [0.0]
  In this paper, we investigate how self-supervision with strong and sufficient augmentation of unlabeled data can train effectively the first layers of a neural network. We show that the low-level features derived from a self-supervised architecture can improve the robustness and the overall performance of this emergent architecture.
  arXiv  Detail & Related papers  (2021-11-08T21:44:31Z)
• Exploiting the relationship between visual and textual features in social networks for image classification with zero-shot deep learning [0.0]
  In this work, we propose a classifier ensemble based on the transferable learning capabilities of the CLIP neural network architecture. Our experiments, based on image classification tasks according to the labels of the Places dataset, are performed by first considering only the visual part. Considering the associated texts to the images can help to improve the accuracy depending on the goal.
  arXiv  Detail & Related papers  (2021-07-08T10:54:59Z)
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision [57.031588264841]
  We leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme.
  arXiv  Detail & Related papers  (2021-02-11T10:08:12Z)
• Self-supervised Learning with Fully Convolutional Networks [24.660086792201263]
  We focus on the problem of learning representation from unlabeled data for semantic segmentation. Inspired by two patch-based methods, we develop a novel self-supervised learning framework. We achieve a 5.8 percentage point improvement over the baseline model.
  arXiv  Detail & Related papers  (2020-12-18T02:31:28Z)
• Self supervised contrastive learning for digital histopathology [0.0]
  We use a contrastive self-supervised learning method called SimCLR that achieved state-of-the-art results on natural-scene images. We find that combining multiple multi-organ datasets with different types of staining and resolution properties improves the quality of the learned features. Linear classifiers trained on top of the learned features show that networks pretrained on digital histopathology datasets perform better than ImageNet pretrained networks.
  arXiv  Detail & Related papers  (2020-11-27T19:18:45Z)
• An analysis of the transfer learning of convolutional neural networks for artistic images [1.9336815376402716]
  Transfer learning from huge natural image datasets has become de facto the core of art analysis applications. In this paper, we first use techniques for visualizing the network internal representations in order to provide clues to the understanding of what the network has learned on artistic images. We provide a quantitative analysis of the changes introduced by the learning process thanks to metrics in both the feature and parameter spaces, as well as metrics computed on the set of maximal activation images.
  arXiv  Detail & Related papers  (2020-11-05T09:45:32Z)
• Adversarially-Trained Deep Nets Transfer Better: Illustration on Image Classification [53.735029033681435]
  Transfer learning is a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. In this work, we demonstrate that adversarially-trained models transfer better than non-adversarially-trained models.
  arXiv  Detail & Related papers  (2020-07-11T22:48:42Z)
• 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)
• Curriculum By Smoothing [52.08553521577014]
  Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. We propose an elegant curriculum based scheme that smoothes the feature embedding of a CNN using anti-aliasing or low-pass filters. As the amount of information in the feature maps increases during training, the network is able to progressively learn better representations of the data.
  arXiv  Detail & Related papers  (2020-03-03T07:27:44Z)

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.