Alert button
Picture for Mingcheng Zhuge

Mingcheng Zhuge

Alert button

Masked Vision-Language Transformer in Fashion

Oct 27, 2022
Ge-Peng Ji, Mingcheng Zhuge, Dehong Gao, Deng-Ping Fan, Christos Sakaridis, Luc Van Gool

Figure 1 for Masked Vision-Language Transformer in Fashion
Figure 2 for Masked Vision-Language Transformer in Fashion
Figure 3 for Masked Vision-Language Transformer in Fashion
Figure 4 for Masked Vision-Language Transformer in Fashion

We present a masked vision-language transformer (MVLT) for fashion-specific multi-modal representation. Technically, we simply utilize vision transformer architecture for replacing the BERT in the pre-training model, making MVLT the first end-to-end framework for the fashion domain. Besides, we designed masked image reconstruction (MIR) for a fine-grained understanding of fashion. MVLT is an extensible and convenient architecture that admits raw multi-modal inputs without extra pre-processing models (e.g., ResNet), implicitly modeling the vision-language alignments. More importantly, MVLT can easily generalize to various matching and generative tasks. Experimental results show obvious improvements in retrieval (rank@5: 17%) and recognition (accuracy: 3%) tasks over the Fashion-Gen 2018 winner Kaleido-BERT. Code is made available at https://github.com/GewelsJI/MVLT.

* Accepted by Machine Intelligence Research (2023) 
Viaarxiv icon