LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations
- URL: http://arxiv.org/abs/2403.06813v2
- Date: Thu, 18 Jul 2024 18:55:51 GMT
- Title: LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations
- Authors: Mohammad Alkhalefi, Georgios Leontidis, Mingjun Zhong,
- Abstract summary: This paper introduces LeOCLR, a framework that employs a new instance discrimination approach and an adapted loss function to alleviate discarding semantic features during representation learning.
Our approach consistently improves representation learning across different datasets compared to baseline models.
- Score: 4.680881326162484
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Contrastive instance discrimination approaches outperform supervised learning in downstream tasks like image classification and object detection. However, these approaches heavily rely on data augmentation during representation learning, which may result in inferior results if not properly implemented. Random cropping followed by resizing is a common form of data augmentation used in contrastive learning, but it can lead to degraded representation learning if the two random crops contain distinct semantic content. To address this issue, this paper introduces LeOCLR (Leveraging Original Images for Contrastive Learning of Visual Representations), a framework that employs a new instance discrimination approach and an adapted loss function to alleviate discarding semantic features caused by mapping different object parts during representation learning. The experimental results show that our approach consistently improves representation learning across different datasets compared to baseline models. For example, our approach outperforms MoCo-v2 by 5.1% on ImageNet-1K in linear evaluation and several other methods on transfer learning tasks.
Related papers
- Semantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination methods [4.680881326162484]
Self-supervised learning algorithms (SSL) based on instance discrimination have shown promising results.
We propose an approach to identify those images with similar semantic content and treat them as positive instances.
We run experiments on three benchmark datasets: ImageNet, STL-10 and CIFAR-10 with different instance discrimination SSL approaches.
arXiv Detail & Related papers (2023-06-28T11:47:08Z) - 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) - Weakly Supervised Contrastive Learning [68.47096022526927]
We introduce a weakly supervised contrastive learning framework (WCL) to tackle this issue.
WCL achieves 65% and 72% ImageNet Top-1 Accuracy using ResNet50, which is even higher than SimCLRv2 with ResNet101.
arXiv Detail & Related papers (2021-10-10T12:03:52Z) - Object-aware Contrastive Learning for Debiased Scene Representation [74.30741492814327]
We develop a novel object-aware contrastive learning framework that localizes objects in a self-supervised manner.
We also introduce two data augmentations based on ContraCAM, object-aware random crop and background mixup, which reduce contextual and background biases during contrastive self-supervised learning.
arXiv Detail & Related papers (2021-07-30T19:24:07Z) - Incremental False Negative Detection for Contrastive Learning [95.68120675114878]
We introduce a novel incremental false negative detection for self-supervised contrastive learning.
During contrastive learning, we discuss two strategies to explicitly remove the detected false negatives.
Our proposed method outperforms other self-supervised contrastive learning frameworks on multiple benchmarks within a limited compute.
arXiv Detail & Related papers (2021-06-07T15:29:14Z) - Few-Shot Learning with Part Discovery and Augmentation from Unlabeled
Images [79.34600869202373]
We show that inductive bias can be learned from a flat collection of unlabeled images, and instantiated as transferable representations among seen and unseen classes.
Specifically, we propose a novel part-based self-supervised representation learning scheme to learn transferable representations.
Our method yields impressive results, outperforming the previous best unsupervised methods by 7.74% and 9.24%.
arXiv Detail & Related papers (2021-05-25T12:22:11Z) - With a Little Help from My Friends: Nearest-Neighbor Contrastive
Learning of Visual Representations [87.72779294717267]
Using the nearest-neighbor as positive in contrastive losses improves performance significantly on ImageNet classification.
We demonstrate empirically that our method is less reliant on complex data augmentations.
arXiv Detail & Related papers (2021-04-29T17:56:08Z) - Contrastive Learning based Hybrid Networks for Long-Tailed Image
Classification [31.647639786095993]
We propose a novel hybrid network structure composed of a supervised contrastive loss to learn image representations and a cross-entropy loss to learn classifiers.
Experiments on three long-tailed classification datasets demonstrate the advantage of the proposed contrastive learning based hybrid networks in long-tailed classification.
arXiv Detail & Related papers (2021-03-26T05:22:36Z) - 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) - 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)
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.