Source-linked AI summary

Competitive Memory Readout for Robust Video Object Segmentation: 2nd Place Technical Report for the MOSEv2 Track of the 8th LSVOS Challenge

Mingqi Gao, Sijie Li, Jungong Han

arXiv:2608.22064v1cs.CV

TL;DR

MOSEv2 challenges video object segmentation when occlusion, disappearance, reappearance, appearance changes, and similar objects make target identity difficult to preserve. The paper augments SAM 3 with Competitive Memory Readout and adaptive restoration, achieving a 66.20 primary challenge score and second place in the track.

  • Problem

    MOSEv2 tests whether a tracker can preserve the annotated target under severe temporal dynamics and visually similar distractors, where target-only memory retrieval can confuse instances.

  • Method

    The method compares SAM 3 target memory with same-class competitor evidence and applies lightweight adaptive restoration when competition suppresses valid weak or reappearing target evidence.

  • Results

    66.20 primary challenge score and 2nd place were achieved in the MOSEv2 track.

  • Takeaways & Limitations

    The resulting system preserves the original SAM 3 tracking pipeline while improving robustness to MOSEv2’s long-term occlusion, disappearance, reappearance, and similar-object interference.

Abstract

from arXiv · show

We present our solution for the MOSEv2 track of the 8th Large-scale Video Object Segmentation (LSVOS) Challenge at ECCV 2026. The challenge evaluates robust video object segmentation under complex temporal dynamics, including long-term occlusion, disappearance and reappearance, large appearance changes, and strong interference from visually similar objects. Our method builds on SAM~3 and focuses on its memory readout. Standard target-only memory retrieval can confuse the annotated target with same-class non-target objects because such distractors are represented only implicitly as background. Our method introduces Competitive Memory Readout, which explicitly incorporates same-class competitor evidence when retrieving target information from memory. To prevent excessive suppression of weak or reappearing targets, we further apply a lightweight adaptive restoration rule after competition. The resulting system retains the original SAM~3 tracking pipeline while improving target identity preservation in challenging videos. Our submission achieves 66.20 on the primary challenge score and ranks 2nd in the MOSEv2 track.

1 Introduction

The MOSEv2 track targets semi-supervised video object segmentation under severe temporal and visual challenges, where preserving the annotated target’s identity is central. Competitive Memory Readout addresses target-centric retrieval by explicitly comparing target evidence with same-class competitors.

  • MOSEv2 evaluates propagation of a first-frame target mask through videos with occlusion, disappearance, reappearance, appearance changes, and similar-object interference.
  • These conditions make identity preservation difficult because plausible masks can gradually drift from the annotated target to a same-class distractor.
  • Standard memory retrieval explicitly represents the target but treats same-class distractors as non-target context, measuring target-history similarity without comparing plausible alternatives.
  • Competitive Memory Readout compares target evidence against same-class competitor evidence during memory retrieval to address identity confusion after occlusion or reappearance.

2 Related Work

Memory-based video object segmentation evolved from direct propagation toward storing and retrieving historical features and masks. The paper’s framing highlights a limitation of target-only retrieval: visually similar non-targets can induce identity drift.

  • Semi-supervised video object segmentation propagates specified target objects from first-frame masks through the remaining video.
  • Memory-based methods became dominant by storing previous features and masks and retrieving them for current-frame prediction.
  • The standard target-only readout does not model visually similar non-target objects as competitors, allowing distractor-supported target responses and identity drift.

3 Method

The method retains SAM 3’s backbone, memory encoder, and mask decoder while replacing target-only retrieval with competitive target-versus-distractor evidence. Adaptive restoration then recovers useful target evidence when competition suppresses it too strongly.

  • 3.1 Overview: Competitive Memory Readout augments SAM 3 target-conditioned retrieval with same-class non-target competitors while leaving the backbone, memory encoder, and mask decoder unchanged.
  • 3.2 Competitive Memory Readout: SAM 3 concept-aware detections provide same-class non-target hypotheses, which are filtered for strong overlap with the tracked target before competitor-token encoding.
  • 3.2 Competitive Memory Readout: For each current-frame token, target and competitor attention logits are aggregated separately with log-sum-exp to form competing evidence.
  • 3.2 Competitive Memory Readout: A competition gate is applied to target foreground logits before original memory-attention normalisation, suppressing target evidence when competitors provide stronger support.
  • 3.2 Competitive Memory Readout: When no valid competitor exists, Competitive Memory Readout reduces to the original target-only readout.
  • 3.3 Adaptive Restoration: Adaptive restoration measures suppression between pre- and post-competition target responses and restores part of the target evidence.
  • 3.3 Adaptive Restoration: The restoration factor ranges from 1.0 to 1.5, increasing recovery as target responses are more heavily suppressed without requiring an additional learned policy.

4 Experiments

Experiments evaluate the method on the official MOSEv2 challenge setting, using first-frame masks and difficult videos with temporal changes and similar objects. The submission ranks second with a primary score of 66.20, while qualitative results show more stable segmentation than SAM 3 on a challenging long sequence.

  • 4.1 Challenge Setting: MOSEv2 experiments follow the semi-supervised protocol, providing first-frame target masks and predicting the same targets in remaining frames.
  • 4.1 Challenge Setting: The challenge videos contain frequent occlusion, disappearance and reappearance, large target variations, and multiple similar objects.
  • 4.1 Challenge Setting: Across frames sampled from the beginning to the end of a challenging long sequence, the method maintains more stable target segmentation than the SAM 3 baseline under appearance variation and distractor interference.
  • 4.3 Challenge Result and Qualitative Analysis: 66.20 primary challenge score and 2nd place were achieved on the MOSEv2 leaderboard.
  • 4.3 Challenge Result and Qualitative Analysis: 81.57 was achieved on the disappearance metric, while reappearance remained substantially more challenging.

5 Conclusion

The 2nd-place MOSEv2 solution augments SAM 3 with Competitive Memory Readout and adaptive restoration to preserve target identity under challenging video conditions. It achieves a primary challenge score of 66.20 while retaining the original SAM 3 tracking pipeline.

  • Competitive Memory Readout compares target memory against same-class competitor evidence to reduce identity drift.It explicitly incorporates plausible non-target alternatives during memory retrieval.
  • Adaptive restoration recovers valid target evidence when competition suppresses weak or reappearing targets too strongly.
  • 66.20 primary challenge score and 2nd-place MOSEv2 ranking demonstrate the submission’s reported challenge outcome.The method preserves the original SAM 3 tracking pipeline while improving robustness to difficult temporal dynamics and similar-object interference.
Loading 2608.22064v1…