{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/maskris-semantic-distortion-aware-data","title":"MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation","arxiv_id":"2411.19067","date":"2024-11-28","proceeding":null,"authors":["Minhyun Lee","Seungho Lee","Song Park","Dongyoon Han","Byeongho Heo","Hyunjung Shim"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2411.19067v1","url_pdf":"https://arxiv.org/pdf/2411.19067v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"maskris-semantic-distortion-aware-data","repo_url":"https://github.com/naver-ai/maskris","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"stochastic-depth","method_name":"Stochastic Depth"},{"method_slug":"swin-transformer","method_name":"Swin Transformer"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-8","task":"Referring Expression Segmentation","dataset":"RefCOCO testA","model":"MaskRIS (Swin-B, combined DB)","rank_in_archive_order":7,"of":13,"metrics":{"Overall IoU":"80.64"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-8","task":"Referring Expression Segmentation","dataset":"RefCOCO testA","model":"MaskRIS (Swin-B)","rank_in_archive_order":8,"of":13,"metrics":{"Mean IoU":"80.24","Overall IoU":"78.96"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-9","task":"Referring Expression Segmentation","dataset":"RefCOCO testB","model":"MaskRIS (Swin-B, combined DB)","rank_in_archive_order":7,"of":13,"metrics":{"Overall IoU":"75.1"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-9","task":"Referring Expression Segmentation","dataset":"RefCOCO testB","model":"MaskRIS (Swin-B)","rank_in_archive_order":8,"of":13,"metrics":{"Mean IoU":"76.06","Overall IoU":"73.96"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-5","task":"Referring Expression Segmentation","dataset":"RefCOCO+ test B","model":"MaskRIS (Swin-B, combined DB)","rank_in_archive_order":11,"of":30,"metrics":{"Overall IoU":"62.83"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-5","task":"Referring Expression Segmentation","dataset":"RefCOCO+ test B","model":"MaskRIS (Swin-B)","rank_in_archive_order":13,"of":30,"metrics":{"Mean IoU":"64.5","Overall IoU":"59.39"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-4","task":"Referring Expression Segmentation","dataset":"RefCOCO+ testA","model":"MaskRIS (Swin-B, combined DB)","rank_in_archive_order":10,"of":30,"metrics":{"Overall IoU":"75.15"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-4","task":"Referring Expression Segmentation","dataset":"RefCOCO+ testA","model":"MaskRIS (Swin-B)","rank_in_archive_order":14,"of":30,"metrics":{"Mean IoU":"76.73","Overall IoU":"74.46"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-3","task":"Referring Expression Segmentation","dataset":"RefCOCO+ val","model":"MaskRIS (Swin-B, combined DB)","rank_in_archive_order":14,"of":33,"metrics":{"Overall IoU":"70.26"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco-3","task":"Referring Expression Segmentation","dataset":"RefCOCO+ val","model":"MaskRIS (Swin-B)","rank_in_archive_order":18,"of":33,"metrics":{"Mean IoU":"71.68","Overall IoU":"67.54"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog-1","task":"Referring Expression Segmentation","dataset":"RefCOCOg-test","model":"MaskRIS (Swin-B, combined DB)","rank_in_archive_order":9,"of":18,"metrics":{"Overall IoU":"71.09"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog-1","task":"Referring Expression Segmentation","dataset":"RefCOCOg-test","model":"MaskRIS (Swin-B)","rank_in_archive_order":13,"of":18,"metrics":{"Mean IoU":"69.42","Overall IoU":"66.5"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog","task":"Referring Expression Segmentation","dataset":"RefCOCOg-val","model":"MaskRIS (Swin-B, combined DB)","rank_in_archive_order":13,"of":23,"metrics":{"Overall IoU":"69.12"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcocog","task":"Referring Expression Segmentation","dataset":"RefCOCOg-val","model":"MaskRIS (Swin-B)","rank_in_archive_order":15,"of":23,"metrics":{"Mean IoU":"69.31","Overall IoU":"65.55"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","task":"Referring Expression Segmentation","dataset":"RefCoCo val","model":"MaskRIS (Swin-B, combined DB)","rank_in_archive_order":13,"of":37,"metrics":{"Overall IoU":"78.71"},"uses_additional_data":false},{"leaderboard":"/sota/referring-expression-segmentation-on-refcoco","task":"Referring Expression Segmentation","dataset":"RefCoCo val","model":"MaskRIS (Swin-B)","rank_in_archive_order":16,"of":37,"metrics":{"Mean IoU":"78.35","Overall IoU":"76.49"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}