Skip to Main content Skip to Navigation
Conference papers

A General Two-Branch Decoder Architecture for Improving Encoder-Decoder Image Segmentation Models

Abstract : Recently, many methods with complex structures were proposed to address image parsing tasks such as image segmentation. These well-designed structures are hardly to be used flexibly and require a heavy footprint. This paper focuses on a popular semantic segmentation framework known as encoder-decoder, and points out a phenomenon that existing decoders do not fully integrate the information extracted by the encoder. To alleviate this issue, we propose a more general two-branch paradigm, composed of a main branch and an auxiliary branch, without increasing the number of parameters, and a boundary enhanced loss computation strategy to make two-branch decoders learn complementary information adaptively instead of explicitly indicating the specific learning element. In addition, one branch learns pixels that are difficult to resolve in another branch making a competition between them, which promotes the model to learn more efficiently. We evaluate our approach on two challenging image segmentation datasets and show its superior performance in different baseline models. We also perform an ablation study to tease apart the effects of different settings. Finally, we show our two-branch paradigm can achieve satisfactory results when remove the auxiliary branch in the inference stage, so that it can be applied to low-resource systems.
Document type :
Conference papers
Complete list of metadata

https://hal-univ-evry.archives-ouvertes.fr/hal-03719446
Contributor : Désiré Sidibé Connect in order to contact the contributor
Submitted on : Monday, July 11, 2022 - 11:25:46 AM
Last modification on : Wednesday, July 20, 2022 - 3:27:09 AM

File

_VISAPP2022__Improving_image_s...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03719446, version 1

Citation

Sijie Hu, Fabien Bonardi, Samia Bouchafa, Désiré Sidibé. A General Two-Branch Decoder Architecture for Improving Encoder-Decoder Image Segmentation Models. VISAPP 2022 : 17th International Conference on Computer Vision Theory and Applications, Feb 2022, Online, Portugal. ⟨hal-03719446⟩

Share

Metrics

Record views

0

Files downloads

0