Papers › Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for...
Memory Matching is not Enough: Jointly Improving Memory Matching and Decoding for Video Object Segmentation
Jintu Zheng, Yun Liang, Yuqing Zhang, Wanchao Su
Memory-based video object segmentation methods model multiple objects over long temporal-spatial spans by establishing memory bank, which achieve the remarkable performance. However, they struggle to overcome the false matching and are prone to lose critical information, resulting in confusion among different objects. In this paper, we propose an effective approach which jointly improving the matching and decoding stages to alleviate the false matching issue.For the memory matching stage, we present a cost aware mechanism that suppresses the slight errors for short-term memory and a shunted cross-scale matching for long-term memory which establish a wide filed matching spaces for various object scales. For the readout decoding stage, we implement a compensatory mechanism aims at recovering the essential information where missing at the matching stage. Our approach achieves the outstanding performance in several popular benchmarks (i.e., DAVIS 2016&2017 Val (92.4%&88.1%), and DAVIS 2017 Test (83.9%)), and achieves 84.8%&84.6% on YouTubeVOS 2018&2019 Val.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semi-Supervised Video Object Segmentation | DAVIS 2017 (test-dev) | JIMD-R50 | F-measure (Mean) | 87.4 | #6 of 59 | Archive leaderboard | report |
| Semi-Supervised Video Object Segmentation | DAVIS 2017 (test-dev) | JIMD-R50 | J&F | 83.9 | #6 of 59 | Archive leaderboard | report |
| Semi-Supervised Video Object Segmentation | DAVIS 2017 (test-dev) | JIMD-R50 | Jaccard (Mean) | 80.3 | #6 of 59 | Archive leaderboard | report |
| Semi-Supervised Video Object Segmentation | DAVIS 2017 (val) | JIMD | F-measure (Mean) | 91.0 | #9 of 81 | Archive leaderboard | report |
| Semi-Supervised Video Object Segmentation | DAVIS 2017 (val) | JIMD | J&F | 88.1 | #9 of 81 | Archive leaderboard | report |
| Semi-Supervised Video Object Segmentation | DAVIS 2017 (val) | JIMD | Jaccard (Mean) | 85.2 | #9 of 81 | 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.
Methods
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