SlotMatch：提取以对象为中心的表示用于无监督视频分割
SlotMatch: Distilling Object-Centric Representations for Unsupervised Video Segmentation
AI总结：
针对无监督视频分割中基于槽注意力的模型计算成本高的问题，提出SlotMatch知识蒸馏框架，将以对象为中心的表示迁移到轻量级学生模型，该学生模型参数减少3.6倍、速度快2.7倍，性能优于教师模型及其他最先进模型。
摘要：
无监督视频分割是一项具有挑战性的计算机视觉任务，尤其是由于缺乏监督信号以及视觉场景的复杂性。为了克服这一挑战，基于槽注意力的最先进模型通常不得不依赖大型且计算成本高昂的神经架构。为此，我们提出了一个简单的知识蒸馏框架，可有效地将以对象为中心的表示迁移到轻量级学生模型中。所提出的框架称为SlotMatch，通过余弦相似度对齐相应的教师和学生槽，不需要额外的蒸馏目标或辅助监督。SlotMatch的简单性通过理论和实证证据得到证实，两者都表明整合额外损失是多余的。我们在三个数据集上进行实验，将最先进的教师模型SlotContrast与我们蒸馏的学生模型进行比较。结果表明，基于SlotMatch的学生模型与教师模型相当甚至优于教师模型，同时使用的参数减少3.6倍，运行速度最高快2.7倍。此外，我们的学生模型优于所有其他最先进的无监督视频分割模型。
英文摘要：
Unsupervised video segmentation is a challenging computer vision task, especially due to the lack of supervisory signals coupled with the complexity of visual scenes. To overcome this challenge, state-of-the-art models based on slot attention often have to rely on large and computationally expensive neural architectures. To this end, we propose a simple knowledge distillation framework that effectively transfers object-centric representations to a lightweight student. The proposed framework, called SlotMatch, aligns corresponding teacher and student slots via the cosine similarity, requiring no additional distillation objectives or auxiliary supervision. The simplicity of SlotMatch is confirmed via theoretical and empirical evidence, both indicating that integrating additional losses is redundant. We conduct experiments on three datasets to compare the state-of-the-art teacher model, SlotContrast, with our distilled student. The results show that our student based on SlotMatch matches and even outperforms its teacher, while using 3.6x less parameters and running up to 2.7x faster. Moreover, our student surpasses all other state-of-the-art unsupervised video segmentation models.
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。
