VINO：通过结构先验引导的去上下文化实现视频驱动的非上下文物体不变性
VINO: Video-driven Invariance for Non-contextual Objects via Structural Prior Guided De-contextualization
AI总结：
VINO通过结构先验引导的去上下文化方法，有效分离视频中前景与背景，提升非上下文物体的表示鲁棒性。
摘要：
自监督学习（SSL）已取得快速进展，但学到的特征往往过度依赖上下文捷径——背景纹理和共现统计信息。虽然视频提供了丰富的时序变化，但密集的野外流体具有强烈的自我运动，会形成共现陷阱：前景物体和背景上下文协调移动，促使表示崩溃到场景编码器中。为了解决这一问题，我们提出了VINO（视频驱动的非上下文物体不变性），一种教师-学生框架，通过施加结构信息瓶颈来学习稳健的图像编码器。使用一个不依赖类别的结构先验仅生成视图——不作为语义伪标签——VINO形成一个非对称蒸馏问题。教师从前景-联合视图中进行预测，背景被抑制；而学生观察到物体条件化的场景视图，保留周围上下文但移除竞争实例。通过掩码蒸馏匹配这些目标使背景线索不可靠，推动表示向以物体为中心的不变性发展。我们进一步通过教师锚定的跨时间蒸馏强化时间物体恒常性，通过掩码引导的局部视图稳定部分到整体的一致性。通过注意力可视化和无监督物体发现于PASCAL VOC，我们证明VINO有效分离前景与背景。在密集的Walking Tours Venice视频上预训练，VINO达到34.8 CorLoc，产生高度聚焦、以形状为导向的表示，显著优于先前的密集视频和运动引导SSL基线。
英文摘要：
Self-supervised learning (SSL) has made rapid progress, yet learned features often over-rely on contextual shortcuts-background textures and co-occurrence statistics. While video provides rich temporal variation, dense in-the-wild streams with strong ego-motion create a co-occurrence trap: foreground objects and background context move coherently, encouraging representations to collapse into scene encoders. To address this, we propose VINO (Video-driven Invariance for Non-Contextual Objects), a teacher-student framework that learns robust image encoders from dense video by imposing a structural information bottleneck. Using a class-agnostic structural prior solely to generate views-not as semantic pseudo-labels-VINO forms an asymmetric distillation problem. The teacher predicts from a foreground-union view with the background suppressed, while the student observes object-conditioned scene views that retain surrounding context but remove competing instances. Matching these targets via masked distillation makes background cues unreliable, pushing the representation toward object-centric invariances. We further enforce temporal object permanence via teacher-anchored cross-time distillation over track-matched objects, and stabilize part-to-whole consistency with mask-guided local views. Through attention visualization and unsupervised object discovery on PASCAL VOC, we demonstrate that VINO effectively disentangles foreground from background. Pretrained on the dense Walking Tours Venice video, VINO achieves 34.8 CorLoc, yielding highly focused, shape-biased representations that substantially outperform prior dense-video and motion-guided SSL baselines.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
