Semantic Information in Contrastive Learning

Shengjiang Quan, Masahiro Hirano, Yuji Yamakawa
2/14/2026

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

This work investigates the functionality of Semantic information in Contrastive Learning (SemCL). An advanced pretext task is designed: a contrast is performed between each object and its environment, taken from a scene. This allows the SemCL pretrained model to extract objects from their environment in an image, significantly improving the spatial understanding of the pretrained models. Downstream tasks of semantic/instance segmentation, object detection and depth estimation are implemented on PASCAl VOC, Cityscapes, COCO, KITTI, etc. SemCL pretrained models substantially outperform ImageNet pretrained counterparts and are competitive with well-known works on downstream tasks. The results suggest that a dedicated pretext task lever-aging semantic information can be powerful in benchmarks related to spatial understanding. The code is available at https://github.com/sjiang95/semcl.

DOISemantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{quan2026semantic,
  title  = {Semantic Information in Contrastive Learning},
  author = {Shengjiang Quan and Masahiro Hirano and Yuji Yamakawa},
  year   = {2026},
  doi    = {10.1109/ICCV51070.2023.00523},
  url    = {https://doi.org/10.1109/ICCV51070.2023.00523},
  journal = {ICCV 2023 2023}
}

Discussion