A General Two-Branch Decoder Architecture for Improving Encoder-Decoder Image Segmentation Models - Archive ouverte HAL Access content directly
Conference Papers Year :

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

(1) , (1) , (1) , (1)
1

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.
Fichier principal
Vignette du fichier
_VISAPP2022__Improving_image_segmentation_models_using_strong_loss_and_a_two_decoder_CNN_architecture.pdf (33.21 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03719446 , version 1 (11-07-2022)

Identifiers

  • HAL Id : hal-03719446 , version 1

Cite

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⟩
18 View
9 Download

Share

Gmail Facebook Twitter LinkedIn More