MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation
This work addresses the underexplored area of data augmentation in RIS, offering a method to enhance model robustness for vision-language tasks, though it is incremental as it builds on existing RIS models.
The paper tackles the problem of improving Referring Image Segmentation (RIS) by proposing MaskRIS, a data augmentation framework using image and text masking with distortion-aware learning, which achieves new state-of-the-art performance on RefCOCO, RefCOCO+, and RefCOCOg datasets.
Referring Image Segmentation (RIS) is an advanced vision-language task that involves identifying and segmenting objects within an image as described by free-form text descriptions. While previous studies focused on aligning visual and language features, exploring training techniques, such as data augmentation, remains underexplored. In this work, we explore effective data augmentation for RIS and propose a novel training framework called Masked Referring Image Segmentation (MaskRIS). We observe that the conventional image augmentations fall short of RIS, leading to performance degradation, while simple random masking significantly enhances the performance of RIS. MaskRIS uses both image and text masking, followed by Distortion-aware Contextual Learning (DCL) to fully exploit the benefits of the masking strategy. This approach can improve the model's robustness to occlusions, incomplete information, and various linguistic complexities, resulting in a significant performance improvement. Experiments demonstrate that MaskRIS can easily be applied to various RIS models, outperforming existing methods in both fully supervised and weakly supervised settings. Finally, MaskRIS achieves new state-of-the-art performance on RefCOCO, RefCOCO+, and RefCOCOg datasets. Code is available at https://github.com/naver-ai/maskris.