LeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations
This addresses a specific bottleneck in contrastive learning for computer vision, offering incremental improvements in tasks like image classification and object detection.
The paper tackled the problem of random cropping degrading semantic content in contrastive learning by introducing LeOCLR, which improved representation learning and outperformed MoCo-v2 by 5.1% on ImageNet-1K.
Contrastive instance discrimination methods outperform supervised learning in downstream tasks such as image classification and object detection. However, these methods rely heavily on data augmentation during representation learning, which can lead to suboptimal results if not implemented carefully. A common augmentation technique in contrastive learning is random cropping followed by resizing. This can degrade the quality of representation learning when the two random crops contain distinct semantic content. To tackle this issue, we introduce LeOCLR (Leveraging Original Images for Contrastive Learning of Visual Representations), a framework that employs a novel instance discrimination approach and an adapted loss function. This method prevents the loss of important semantic features caused by mapping different object parts during representation learning. Our experiments demonstrate that LeOCLR consistently improves representation learning across various datasets, outperforming baseline models. For instance, LeOCLR surpasses MoCo-v2 by 5.1% on ImageNet-1K in linear evaluation and outperforms several other methods on transfer learning and object detection tasks.