Improving Transformation Invariance in Contrastive Representation Learning

• URL: http://arxiv.org/abs/2010.09515v2
• Date: Mon, 22 Mar 2021 14:20:51 GMT
• Title: Improving Transformation Invariance in Contrastive Representation Learning
• Authors: Adam Foster, Rattana Pukdee, Tom Rainforth
• Abstract summary: We introduce a training objective for contrastive learning that uses a novel regularizer to control how the representation changes under transformation. Second, we propose a change to how test time representations are generated by introducing a feature averaging approach that combines encodings from multiple transformations of the original input. Third, we introduce the novel Spirograph dataset to explore our ideas in the context of a differentiable generative process with multiple downstream tasks.
• Score: 31.223892428863238
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose methods to strengthen the invariance properties of representations obtained by contrastive learning. While existing approaches implicitly induce a degree of invariance as representations are learned, we look to more directly enforce invariance in the encoding process. To this end, we first introduce a training objective for contrastive learning that uses a novel regularizer to control how the representation changes under transformation. We show that representations trained with this objective perform better on downstream tasks and are more robust to the introduction of nuisance transformations at test time. Second, we propose a change to how test time representations are generated by introducing a feature averaging approach that combines encodings from multiple transformations of the original input, finding that this leads to across the board performance gains. Finally, we introduce the novel Spirograph dataset to explore our ideas in the context of a differentiable generative process with multiple downstream tasks, showing that our techniques for learning invariance are highly beneficial.

Related papers

• Latent Space Translation via Semantic Alignment [29.2401314068038]
  We show how representations learned from different neural modules can be translated between different pre-trained networks. Our method directly estimates a transformation between two given latent spaces, thereby enabling effective stitching of encoders and decoders without additional training. Notably, we show how it is possible to zero-shot stitch text encoders and vision decoders, or vice-versa, yielding surprisingly good classification performance in this multimodal setting.
  arXiv  Detail & Related papers  (2023-11-01T17:12:00Z)
• 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)
• Invariant Causal Mechanisms through Distribution Matching [86.07327840293894]
  In this work we provide a causal perspective and a new algorithm for learning invariant representations. Empirically we show that this algorithm works well on a diverse set of tasks and in particular we observe state-of-the-art performance on domain generalization.
  arXiv  Detail & Related papers  (2022-06-23T12:06:54Z)
• Transformation Coding: Simple Objectives for Equivariant Representations [17.544323284367927]
  We present a non-generative approach to deep representation learning that seeks equivariant deep embedding through simple objectives. In contrast to existing equivariant networks, our transformation coding approach does not constrain the choice of the feed-forward layer or the architecture.
  arXiv  Detail & Related papers  (2022-02-19T01:43:13Z)
• Why Do Self-Supervised Models Transfer? Investigating the Impact of Invariance on Downstream Tasks [79.13089902898848]
  Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. We show that different tasks in computer vision require features to encode different (in)variances.
  arXiv  Detail & Related papers  (2021-11-22T18:16:35Z)
• Disentangled Contrastive Learning for Learning Robust Textual Representations [13.880693856907037]
  We introduce the concept of momentum representation consistency to align features and leverage power normalization while conforming the uniformity. Our experimental results for the NLP benchmarks demonstrate that our approach can obtain better results compared with the baselines.
  arXiv  Detail & Related papers  (2021-04-11T03:32:49Z)
• Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot Learning [96.75889543560497]
  In many real-world problems, collecting a large number of labeled samples is infeasible. Few-shot learning is the dominant approach to address this issue, where the objective is to quickly adapt to novel categories in presence of a limited number of samples. We propose a novel training mechanism that simultaneously enforces equivariance and invariance to a general set of geometric transformations.
  arXiv  Detail & Related papers  (2021-03-01T21:14:33Z)
• Few-shot Sequence Learning with Transformers [79.87875859408955]
  Few-shot algorithms aim at learning new tasks provided only a handful of training examples. In this work we investigate few-shot learning in the setting where the data points are sequences of tokens. We propose an efficient learning algorithm based on Transformers.
  arXiv  Detail & Related papers  (2020-12-17T12:30:38Z)
• Demystifying Contrastive Self-Supervised Learning: Invariances, Augmentations and Dataset Biases [34.02639091680309]
  Recent gains in performance come from training instance classification models, treating each image and it's augmented versions as samples of a single class. We demonstrate that approaches like MOCO and PIRL learn occlusion-invariant representations. Second, we demonstrate that these approaches obtain further gains from access to a clean object-centric training dataset like Imagenet.
  arXiv  Detail & Related papers  (2020-07-28T00:11:31Z)
• On Compositions of Transformations in Contrastive Self-Supervised Learning [66.15514035861048]
  In this paper, we generalize contrastive learning to a wider set of transformations. We find that being invariant to certain transformations and distinctive to others is critical to learning effective video representations.
  arXiv  Detail & Related papers  (2020-03-09T17:56:49Z)

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.