LeJEPA 编码器退化时，无标签监控信号几乎全部失灵
Improving Signals, Declining Encoder: A Known-Answer Test of Label-Free Monitoring in Self-Supervised Learning
训练自监督模型时只看 loss 可能掩盖编码器退化，这篇论文用已知答案测试直接验证了这点，做表征学习的人该看看。
arXiv 论文用带已知生成因子的合成图像训练 LeJEPA 编码器，构造了一个编码器退化的已知答案测试。在 10 个随机种子中有 9 个出现因子可读性骤降，且多沿因子空间同一方向发生。论文同时追踪 11 种无标签监控信号，多数信号持续改善，甚至给退化 run 打出更高分。标准变化点检测也很少在退化起始附近报警，按这些信号挑选 checkpoint 时大多选中退化之后的版本。
Improving Signals, Declining Encoder: A Known-Answer Test of Label-Free Monitoring in Self-Supervised Learning
Self-supervised training is monitored without labels, through the loss and statistics of the learned features. We report a case where we know the encoders lost part of what they had learned, so we can check whether these signals noticed. We trained LeJEPA encoders on synthetic images with known generating factors. In nine of ten seeds, the readability of those factors fell abruptly and stayed down, nearly always along the same direction in factor space. Meanwhile the loss kept falling, and most of the eleven label-free signals we tracked kept improving and rated the declining runs better than runs that did not decline. Standard change-point detection rarely flagged the decline near its onset, and selecting checkpoints by these signals mostly chose ones after it.
