Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations

• URL: http://arxiv.org/abs/2006.10803v2
• Date: Tue, 1 Dec 2020 19:39:24 GMT
• Title: Supervision Accelerates Pre-training in Contrastive Semi-Supervised Learning of Visual Representations
• Authors: Mahmoud Assran, Nicolas Ballas, Lluis Castrejon, Michael Rabbat
• Abstract summary: We propose a semi-supervised loss, SuNCEt, that aims to distinguish examples of different classes in addition to self-supervised instance-wise pretext tasks. On ImageNet, we find that SuNCEt can be used to match the semi-supervised learning accuracy of previous contrastive approaches. Our main insight is that leveraging even a small amount of labeled data during pre-training, and not only during fine-tuning, provides an important signal.
• Score: 12.755943669814236
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We investigate a strategy for improving the efficiency of contrastive learning of visual representations by leveraging a small amount of supervised information during pre-training. We propose a semi-supervised loss, SuNCEt, based on noise-contrastive estimation and neighbourhood component analysis, that aims to distinguish examples of different classes in addition to the self-supervised instance-wise pretext tasks. On ImageNet, we find that SuNCEt can be used to match the semi-supervised learning accuracy of previous contrastive approaches while using less than half the amount of pre-training and compute. Our main insight is that leveraging even a small amount of labeled data during pre-training, and not only during fine-tuning, provides an important signal that can significantly accelerate contrastive learning of visual representations. Our code is available online at github.com/facebookresearch/suncet.

Related papers

• Learning Future Representation with Synthetic Observations for Sample-efficient Reinforcement Learning [12.277005054008017]
  In visual Reinforcement Learning (RL), upstream representation learning largely determines the effect of downstream policy learning. We try to improve auxiliary representation learning for RL by enriching auxiliary training data. We propose a training-free method to synthesize observations that may contain future information. The remaining synthetic observations and real observations then serve as the auxiliary data to achieve a clustering-based temporal association task.
  arXiv  Detail & Related papers  (2024-05-20T02:43:04Z)
• In-Domain Self-Supervised Learning Improves Remote Sensing Image Scene Classification [5.323049242720532]
  Self-supervised learning has emerged as a promising approach for remote sensing image classification. We present a study of different self-supervised pre-training strategies and evaluate their effect across 14 downstream datasets.
  arXiv  Detail & Related papers  (2023-07-04T10:57:52Z)
• Tradeoffs Between Contrastive and Supervised Learning: An Empirical Study [9.520526500374842]
  Contrastive learning has made considerable progress in computer vision, outperforming supervised pretraining on a range of downstream datasets. We demonstrate two cases where it is not. First, under sufficiently small pretraining budgets, supervised pretraining on ImageNet consistently outperforms a comparable contrastive model on eight diverse image classification datasets. Second, even with larger pretraining budgets we identify tasks where supervised learning prevails, perhaps because the object-centric bias of supervised pretraining makes the model more resilient to common corruptions and spurious foreground-background correlations.
  arXiv  Detail & Related papers  (2021-12-10T05:19:32Z)
• Dense Contrastive Visual-Linguistic Pretraining [53.61233531733243]
  Several multimodal representation learning approaches have been proposed that jointly represent image and text. These approaches achieve superior performance by capturing high-level semantic information from large-scale multimodal pretraining. We propose unbiased Dense Contrastive Visual-Linguistic Pretraining to replace the region regression and classification with cross-modality region contrastive learning.
  arXiv  Detail & Related papers  (2021-09-24T07:20:13Z)
• Efficient Visual Pretraining with Contrastive Detection [31.444554574326283]
  We introduce a new self-supervised objective, contrastive detection, which tasks representations with identifying object-level features across augmentations. This objective extracts a rich learning signal per image, leading to state-of-the-art transfer performance from ImageNet to COCO. In particular, our strongest ImageNet-pretrained model performs on par with SEER, one of the largest self-supervised systems to date.
  arXiv  Detail & Related papers  (2021-03-19T14:05:12Z)
• Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations [183.03278932562438]
  This paper presents an effective approach that adds spatial information to the encoding stage to alleviate the learning inconsistency between the contrastive objective and strong data augmentation operations. We show that our approach achieves higher efficiency in visual representations and thus delivers a key message to inspire the future research of self-supervised visual representation learning.
  arXiv  Detail & Related papers  (2020-11-19T16:26:25Z)
• Can Semantic Labels Assist Self-Supervised Visual Representation Learning? [194.1681088693248]
  We present a new algorithm named Supervised Contrastive Adjustment in Neighborhood (SCAN) In a series of downstream tasks, SCAN achieves superior performance compared to previous fully-supervised and self-supervised methods. Our study reveals that semantic labels are useful in assisting self-supervised methods, opening a new direction for the community.
  arXiv  Detail & Related papers  (2020-11-17T13:25:00Z)
• Robust Pre-Training by Adversarial Contrastive Learning [120.33706897927391]
  Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness. We improve robustness-aware self-supervised pre-training by learning representations consistent under both data augmentations and adversarial perturbations.
  arXiv  Detail & Related papers  (2020-10-26T04:44:43Z)
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments [57.33699905852397]
  We propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Our method simultaneously clusters the data while enforcing consistency between cluster assignments. Our method can be trained with large and small batches and can scale to unlimited amounts of data.
  arXiv  Detail & Related papers  (2020-06-17T14:00:42Z)
• Pre-training Text Representations as Meta Learning [113.3361289756749]
  We introduce a learning algorithm which directly optimize model's ability to learn text representations for effective learning of downstream tasks. We show that there is an intrinsic connection between multi-task pre-training and model-agnostic meta-learning with a sequence of meta-train steps.
  arXiv  Detail & Related papers  (2020-04-12T09:05:47Z)

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.