Semi-Supervised Semantic Segmentation (S4) aims to train a segmentation model with limited labeled images and a substantial volume of unlabeled images. To improve the robustness of representations, powerful methods introduce a pixel-wise contrastive learning approach in latent space (i.e., representation space) that aggregates the representations to their prototypes in a fully supervised manner. However, previous contrastive-based S4 methods merely rely on the supervision from the model’s output (logits) in logit space during unlabeled training. In contrast, we utilize the outputs in both logit space and representation space to obtain supervision in a collaborative way. The supervision from two spaces plays two roles: 1) reduces the risk of over-fitting to incorrect semantic information in logits with the help of representations; 2) enhances the knowledge exchange between the two spaces. Furthermore, unlike previous approaches, we use the similarity between representations and prototypes as a new indicator to tilt training those under-performing representations and achieve a more efficient contrastive learning process. Results on two public benchmarks demonstrate the competitive performance of our method compared with state-of-the-art methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation


    Beteiligte:
    Wang, Changqi (Autor:in) / Xie, Haoyu (Autor:in) / Yuan, Yuhui (Autor:in) / Fu, Chong (Autor:in) / Yue, Xiangyu (Autor:in)


    Erscheinungsdatum :

    01.10.2023


    Format / Umfang :

    18357346 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Space Engage: Collaborative Space Supervision for Contrastive-based Semi-Supervised Semantic Segmentation

    Wang, Changqi / Xie, Haoyu / Yuan, Yuhui et al. | ArXiv | 2023

    Freier Zugriff


    Color-Based Free-Space Segmentation Using Online Disparity-Supervised Learning

    Sanberg, Willem P. / Dubbelman, Gijs / With, Peter H. N. de | IEEE | 2015


    Optimal feature space for semantic image segmentation

    Anishchenko, S. I. / Petrushan, M. V. | British Library Online Contents | 2014


    A Deeply Supervised Semantic Segmentation Method Based on GAN

    Zhao, Wei / Wei, Qiyu / Zeng, Zeng | IEEE | 2023