How Severe is Benchmark-Sensitivity in Video Self-Supervised Learning?

Despite the recent success of video self-supervised learning models, there is much still to be understood about their generalization capability. In this paper, we investigate how sensitive video self-supervised learning is to the current conventional benchmark and whether methods generalize beyond the canonical evaluation setting. We do this across four different factors of sensitivity: domain, <PRE_TAG>samples</POST_TAG>, actions and task. Our study which encompasses over 500 experiments on 7 video datasets, 9 self-supervised methods and 6 video understanding tasks, reveals that current benchmarks in video self-supervised learning are not good indicators of generalization along these sensitivity factors. Further, we find that self-supervised methods considerably lag behind vanilla supervised pre-training, especially when <PRE_TAG>domain shift</POST_TAG> is large and the amount of available downstream <PRE_TAG>samples</POST_TAG> are low. From our analysis, we distill the SEVERE-<PRE_TAG>benchmark</POST_TAG>, a subset of our experiments, and discuss its implication for evaluating the generalizability of representations obtained by existing and future self-supervised video learning methods.