提出隐式循环一致性，解决视频物体中心学习中的特征坍缩问题。
Cycle Consistency in Video Object-Centric Learning
- 将循环一致性从离散槽空间转移至连续重建流形，避免刚性对齐
- 在复杂视频数据集上显著缓解特征坍缩，性能超越显式循环一致性基线
- 适合从事自监督视频理解、物体中心学习的研究者参考
自监督视频物体中心学习（OCL）旨在发现独立物体并跨时间关联它们，而自监督多物体跟踪（MOT）则聚焦于关联预定义的物体检测或分割结果。尽管循环一致性（CC）在MOT中已成熟应用，但无法直接应用于OCL的潜在槽空间。与MOT中确定性的理想物体表示不同，OCL槽因场景分解不唯一而具有固有的随机性和模糊性。在槽空间上施加显式循环一致性（ECC）会强制均值寻找，严重惩罚模型探索其他同样有效的分解方式，导致特征坍缩。为解决这一矛盾，我们提出隐式循环一致性（ICC），将循环一致性约束从限制性的槽空间转移到连续重建流形，鼓励槽在共同解释视觉场景上达成软共识，而非强制刚性的点对点特征对齐。在复杂视频OCL基准上的大量实验表明，ICC有效避免特征坍缩，优于ECC基线。源代码、模型检查点和训练日志已发布于https://github.com/Genera1Z/ICC。
原文摘要 · Abstract (English)
Self-supervised video Object-Centric Learning (OCL) aims to discover distinct objects and associate them across time, whereas self-supervised Multi-Object Tracking (MOT) focuses on associating pre-defined object detections or segmentations. Although well-established in MOT, Cycle Consistency (CC) cannot naively or explicitly apply to the latent slot space of OCL. Unlike the deterministic and ideal object representations in MOT, OCL slots are inherently stochastic and ambiguous due to non-unique scene decompositions. Enforcing explicit cycle consistency (ECC) on slots imposes rigid mean seeking. This severely penalizes the model for exploring alternative but equally valid decompositions, thereby driving towards feature collapse. To resolve this dilemma, we propose \textit{Implicit Cycle Consistency (ICC)}, which shifts the cycle-consistency constraint from the restrictive slot space to the continuous reconstruction manifold, encouraging slots to reach a soft consensus on collectively interpreting the visual scene rather than forcing rigid point-to-point feature alignment. Extensive experiments on complex video OCL benchmarks demonstrate that ICC avoids feature collapse and outperforms ECC baselines. Our source code, model checkpoints and training logs are provided on https://github.com/Genera1Z/ICC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。