</> Code with Papers by Syntology

Papers › DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation...

DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy

2 Jul 2025arXiv:2507.01738archive 2025-07-28

Ming Dai, Wenxuan Cheng, Jiang-Jiang Liu, Sen yang, Wenxiao Cai, Yanpeng Sun, Wankou Yang

Referring Image Segmentation (RIS) is a challenging task that aims to segment objects in an image based on natural language expressions. While prior studies have predominantly concentrated on improving vision-language interactions and achieving fine-grained localization, a systematic analysis of the fundamental bottlenecks in existing RIS frameworks remains underexplored. To bridge this gap, we propose DeRIS, a novel framework that decomposes RIS into two key components: perception and cognition. This modular decomposition facilitates a systematic analysis of the primary bottlenecks impeding RIS performance. Our findings reveal that the predominant limitation lies not in perceptual deficiencies, but in the insufficient multi-modal cognitive capacity of current models. To mitigate this, we propose a Loopback Synergy mechanism, which enhances the synergy between the perception and cognition modules, thereby enabling precise segmentation while simultaneously improving robust image-text comprehension. Additionally, we analyze and introduce a simple non-referent sample conversion data augmentation to address the long-tail distribution issue related to target existence judgement in general scenarios. Notably, DeRIS demonstrates inherent adaptability to both non- and multi-referents scenarios without requiring specialized architectural modifications, enhancing its general applicability. The codes and models are available at https://github.com/Dmmm1997/DeRIS.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Dmmm1997/DeRIS officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Data AugmentationGeneralized Referring Expression SegmentationImage SegmentationReading ComprehensionReferring Expression SegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Generalized Referring Expression Segmentation gRefCOCO DeRIS-L cIoU 72.00 #1 of 13 Archive leaderboard report
Generalized Referring Expression Segmentation gRefCOCO DeRIS-L gIoU 77.67 #1 of 13 Archive leaderboard report
Referring Expression Segmentation RefCOCO testA DeRIS-L Mean IoU 86.64 #1 of 13 Archive leaderboard report
Referring Expression Segmentation RefCOCO testA DeRIS-L Overall IoU 86.49 #1 of 13 Archive leaderboard report
Referring Expression Segmentation RefCOCO testB DeRIS-L Mean IoU 84.52 #2 of 13 Archive leaderboard report
Referring Expression Segmentation RefCOCO testB DeRIS-L Overall IoU 82.87 #2 of 13 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ test B DeRIS-L Mean IoU 78.59 #29 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ testA DeRIS-L Mean IoU 83.74 #3 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ testA DeRIS-L Overall IoU 82.34 #3 of 30 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val DeRIS-L Mean IoU 81.28 #2 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCO+ val DeRIS-L Overall IoU 79.01 #2 of 33 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-test DeRIS-L Mean IoU 81.32 #17 of 18 Archive leaderboard report
Referring Expression Segmentation RefCOCOg-val DeRIS-L Mean IoU 80.01 #22 of 23 Archive leaderboard report
Referring Expression Segmentation RefCoCo val DeRIS-L Mean IoU 85.72 #1 of 37 Archive leaderboard report
Referring Expression Segmentation RefCoCo val DeRIS-L Overall IoU 85.41 #1 of 37 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections