Residual Relaxation for Multi-view Representation Learning

• URL: http://arxiv.org/abs/2110.15348v1
• Date: Thu, 28 Oct 2021 17:57:17 GMT
• Title: Residual Relaxation for Multi-view Representation Learning
• Authors: Yifei Wang, Zhengyang Geng, Feng Jiang, Chuming Li, Yisen Wang, Jiansheng Yang, Zhouchen Lin
• Abstract summary: Multi-view methods learn by aligning multiple views of the same image. Some useful augmentations, such as image rotation, are harmful for multi-view methods because they cause a semantic shift. We develop a generic approach, Pretext-aware Residual Relaxation (Prelax), that relaxes the exact alignment.
• Score: 64.40142301026805
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-view methods learn representations by aligning multiple views of the same image and their performance largely depends on the choice of data augmentation. In this paper, we notice that some other useful augmentations, such as image rotation, are harmful for multi-view methods because they cause a semantic shift that is too large to be aligned well. This observation motivates us to relax the exact alignment objective to better cultivate stronger augmentations. Taking image rotation as a case study, we develop a generic approach, Pretext-aware Residual Relaxation (Prelax), that relaxes the exact alignment by allowing an adaptive residual vector between different views and encoding the semantic shift through pretext-aware learning. Extensive experiments on different backbones show that our method can not only improve multi-view methods with existing augmentations, but also benefit from stronger image augmentations like rotation.

Related papers

• CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition [73.51329037954866]
  We propose a robust global representation method with cross-image correlation awareness for visual place recognition. Our method uses the attention mechanism to correlate multiple images within a batch. Our method outperforms state-of-the-art methods by a large margin with significantly less training time.
  arXiv  Detail & Related papers  (2024-02-29T15:05:11Z)
• Effective Data Augmentation With Diffusion Models [65.09758931804478]
  We address the lack of diversity in data augmentation with image-to-image transformations parameterized by pre-trained text-to-image diffusion models. Our method edits images to change their semantics using an off-the-shelf diffusion model, and generalizes to novel visual concepts from a few labelled examples. We evaluate our approach on few-shot image classification tasks, and on a real-world weed recognition task, and observe an improvement in accuracy in tested domains.
  arXiv  Detail & Related papers  (2023-02-07T20:42:28Z)
• Unsupervised Feature Clustering Improves Contrastive Representation Learning for Medical Image Segmentation [18.75543045234889]
  Self-supervised instance discrimination is an effective contrastive pretext task to learn feature representations and address limited medical image annotations. We propose a new self-supervised contrastive learning method that uses unsupervised feature clustering to better select positive and negative image samples. Our method outperforms state-of-the-art self-supervised contrastive techniques on these tasks.
  arXiv  Detail & Related papers  (2022-11-15T22:54:29Z)
• Multimodal contrastive learning for remote sensing tasks [0.5801044612920815]
  We propose a dual-encoder framework, which is pre-trained on a large unlabeled dataset (1M) of Sentinel-1 and Sentinel-2 image pairs. We test the embeddings on two remote sensing downstream tasks: flood segmentation and land cover mapping, and empirically show that embeddings learnt from this technique outperform the conventional technique of collecting positive examples via aggressive data augmentations.
  arXiv  Detail & Related papers  (2022-09-06T09:31:45Z)
• R\'enyiCL: Contrastive Representation Learning with Skew R\'enyi Divergence [78.15455360335925]
  We present a new robust contrastive learning scheme, coined R'enyiCL, which can effectively manage harder augmentations. Our method is built upon the variational lower bound of R'enyi divergence. We show that R'enyi contrastive learning objectives perform innate hard negative sampling and easy positive sampling simultaneously.
  arXiv  Detail & Related papers  (2022-08-12T13:37:05Z)
• Masked Autoencoders are Robust Data Augmentors [90.34825840657774]
  Regularization techniques like image augmentation are necessary for deep neural networks to generalize well. We propose a novel perspective of augmentation to regularize the training process. We show that utilizing such model-based nonlinear transformation as data augmentation can improve high-level recognition tasks.
  arXiv  Detail & Related papers  (2022-06-10T02:41:48Z)
• CORE: Consistent Representation Learning for Face Forgery Detection [11.750814179329343]
  Face manipulation techniques develop rapidly and arouse widespread public concerns. Despite that vanilla convolutional neural networks achieve acceptable performance, they suffer from the overfitting issue. To relieve this issue, there is a trend to introduce some erasing-based augmentations. We find that these methods indeed attempt to implicitly induce more consistent representations for different augmentations. However, due to the lack of explicit regularization, the consistency between different representations is less satisfactory.
  arXiv  Detail & Related papers  (2022-06-06T17:15:56Z)
• Improving Transferability of Representations via Augmentation-Aware Self-Supervision [117.15012005163322]
  AugSelf is an auxiliary self-supervised loss that learns the difference of augmentation parameters between two randomly augmented samples. Our intuition is that AugSelf encourages to preserve augmentation-aware information in learned representations, which could be beneficial for their transferability. AugSelf can easily be incorporated into recent state-of-the-art representation learning methods with a negligible additional training cost.
  arXiv  Detail & Related papers  (2021-11-18T10:43:50Z)

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.