面向无约束第一人称视频的稳定自监督物体表征
Towards Stable Self-Supervised Object Representations in Unconstrained Egocentric Video
用帧内蒸馏加深度正则化从无标注第一人称视频中自举出稳定的『原型物体』表征，并用教师过滤的时序一致性维持身份，可直接迁移到无监督目标发现与自监督预训练的表征稳定化环节。
原文依据 EgoViT bootstraps this learning process by jointly discovering and stabilizing "proto-objects" through three synergistic mechanisms
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人类通过感知环境并与环境交互来发展视觉智能——这是一个植根于第一人称经验的自监督学习过程。受此启发，我们提出如下问题：人工系统如何在不依赖人工标注的情况下，从连续、未经整理的第一人称视频中学习稳定的物体表征。该设定带来的挑战在于：如何在杂乱、遮挡与自运动之中分离、识别并持续跟踪物体。我们提出 EgoViT，一个统一的视觉 Transformer 框架，旨在从无标注的第一人称视频中学习稳定的物体表征。EgoViT 通过三种协同机制联合发现并稳定「原型物体」，从而自举这一学习过程：(1) 原型物体学习，利用帧内蒸馏形成具有判别性的表征；(2) 深度正则化，将这些表征锚定在几何结构之上；(3) 教师过滤的时序一致性，在时间维度上强制身份一致。这形成了一个良性循环，使初始的物体假设被逐步精炼为稳定、持久的表征。该框架在无标注的第一人称视频上端到端训练，并对来源与质量各异的几何先验表现出鲁棒性。在标准基准上，EgoViT 在无监督目标发现上取得 +8.0% 的 CorLoc 提升，在语义分割上取得 +4.8% 的平均交并比提升，显示出其为具身智能中鲁棒的视觉抽象奠定基础的潜力。
英文原文摘要 1540 字符
Humans develop visual intelligence through perceiving and interacting with their environment--a self-supervised learning process grounded in egocentric experience. Inspired by this, we ask how can artificial systems learn stable object representations from continuous, uncurated first-person videos without relying on manual annotations. This setting poses challenges of separating, recognizing, and persistently tracking objects amid clutter, occlusion, and ego-motion. We propose EgoViT, a unified vision Transformer framework designed to learn stable object representations from unlabeled egocentric video. EgoViT bootstraps this learning process by jointly discovering and stabilizing "proto-objects" through three synergistic mechanisms: (1) Proto-object Learning, which uses intra-frame distillation to form discriminative representations; (2) Depth Regularization, which grounds these representations in geometric structure; and (3) Teacher-Filtered Temporal Consistency, which enforces identity over time. This creates a virtuous cycle where initial object hypotheses are progressively refined into stable, persistent representations. The framework is trained end-to-end on unlabeled first-person videos and exhibits robustness to geometric priors of varied origin and quality. On standard benchmarks, EgoViT achieves +8.0% CorLoc improvement in unsupervised object discovery and +4.8% mIoU improvement in semantic segmentation, demonstrating its potential to lay a foundation for robust visual abstraction in embodied intelligence.