mlsanityData to 14 Oct 2026

Video Object Segmentation with Adaptive Feature Bank and Uncertain-Region Refinement

arXiv 2010.07958 ↗First posted 15 Oct 2020cs.CVcited by 101

Not on the map. Why?

Abstract (arXiv)

We propose a new matching-based framework for semi-supervised video object segmentation (VOS). Recently, state-of-the-art VOS performance has been achieved by matching-based algorithms, in which feature banks are created to store features for region matching and classification. However, how to effectively organize information in the continuously growing feature bank remains under-explored, and this leads to inefficient design of the bank. We introduce an adaptive feature bank update scheme to dynamically absorb new features and discard obsolete features. We also design a new confidence loss and a fine-grained segmentation module to enhance the segmentation accuracy in uncertain regions. On public benchmarks, our algorithm outperforms existing state-of-the-arts.

Key facts. Cited by 101 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 13; 2022: 22; 2023: 29; 2024: 20; 2025: 14; 2026: 3.

101 papers.

Sort:

By area:

  1. 2022XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Modelcited by 439
  2. 2023Personalize Segment Anything Model with One Shotcited by 250
  3. 2021Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentationcited by 203
  4. 2023SegGPT: Segmenting Everything In Contextcited by 194
  5. 2023Putting the Object Back into Video Object Segmentationcited by 188
  6. 2023Matcher: Segment Anything with One Shot Using All-Purpose Feature Matchingcited by 142
  7. 2021A Survey on Deep Learning Technique for Video Segmentationcited by 132
  8. 2023Segment Anything Meets Point Trackingcited by 81
  9. 2024SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Treecited by 80
  10. 2022LVOS: A Benchmark for Long-term Video Object Segmentationcited by 77
  11. 2021Hierarchical Memory Matching Network for Video Object Segmentationcited by 72
  12. 2021Learning Position and Target Consistency for Memory-based Video Object Segmentationcited by 63
38 more
  1. 2022Correlation-Aware Deep Trackingcited by 62
  2. 2023XMem++: Production-level Video Segmentation From Few Annotated Framescited by 53
  3. 2022Recurrent Dynamic Embedding for Video Object Segmentationcited by 52
  4. 2024Vivim: a Video Vision Mamba for Medical Video Segmentationcited by 52
  5. 2022Breaking the "Object" in Video Object Segmentationcited by 49
  6. 2024LVOS: A Benchmark for Large-scale Long-term Video Object Segmentationcited by 44
  7. 2022Per-Clip Video Object Segmentationcited by 40
  8. 2022Hierarchical Feature Alignment Network for Unsupervised Video Object Segmentationcited by 37
  9. 2021Reliable Propagation-Correction Modulation for Video Object Segmentationcited by 36
  10. 2022Learning Quality-aware Dynamic Memory for Video Object Segmentationcited by 35
  11. 2022Look Before You Match: Instance Understanding Matters in Video Object Segmentationcited by 34
  12. 2023Scalable Video Object Segmentation with Simplified Frameworkcited by 29
  13. 2022Locality-Aware Inter-and Intra-Video Reconstruction for Self-Supervised Correspondence Learningcited by 26
  14. 2022SWEM: Towards Real-Time Video Object Segmentation with Sequential Weighted Expectation-Maximizationcited by 26
  15. 2025Advancing Complex Video Object Segmentation via Progressive Concept Constructioncited by 26
  16. 2022Global Spectral Filter Memory Network for Video Object Segmentationcited by 22
  17. 2023UniRef++: Segment Every Reference Object in Spatial and Temporal Spacescited by 22
  18. 2024RMem: Restricted Memory Banks Improve Video Object Segmentationcited by 22
  19. 2021VIL-100: A New Dataset and A Baseline Model for Video Instance Lane Detectioncited by 21
  20. 2021HODOR: High-level Object Descriptors for Object Re-segmentation in Video Learned from Static Imagescited by 21
  21. 2023Boosting Video Object Segmentation via Space-time Correspondence Learningcited by 21
  22. 2025EdgeTAM: On-Device Track Anything Modelcited by 21
  23. 2022Region Aware Video Object Segmentation with Deep Motion Modelingcited by 19
  24. 2024A Simple Image Segmentation Framework via In-Context Examplescited by 19
  25. 2022Scalable Video Object Segmentation with Identification Mechanismcited by 18
  26. 2023PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentationcited by 18
  27. 2022Tackling Background Distraction in Video Object Segmentationcited by 16
  28. 2022Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overviewcited by 16
  29. 2023MobileVOS: Real-Time Video Object Segmentation Contrastive Learning meets Knowledge Distillationcited by 16
  30. 2023Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentationcited by 16
  31. 2023Shifting More Attention to Breast Lesion Segmentation in Ultrasound Videoscited by 16
  32. 2021TransVOS: Video Object Segmentation with Transformerscited by 15
  33. 2022BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentationcited by 14
  34. 2023ADNet: Lane Shape Prediction via Anchor Decompositioncited by 14
  35. 2024Temporally Consistent Referring Video Object Segmentation with Hybrid Memorycited by 14
  36. 2024Biomedical SAM 2: Segment Anything in Biomedical Images and Videoscited by 14
  37. 2023ARKitTrack: A New Diverse Dataset for Tracking Using Mobile RGB-D Datacited by 12
  38. 2021Self-Supervised Video Object Segmentation by Motion-Aware Mask Propagationcited by 11

50 most cited of 101 All 101 (JSON)