Uncertainty-aware Unsupervised Video Hashing
Uncertainty-aware Unsupervised Video Hashing
复制标题
DOI：
--
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Yucheng Wang;Mingyuan Zhou;Yu Sun;Xiaoning Qian
中科院分区：
文献类型：
--
作者：
Yucheng Wang;Mingyuan Zhou;Yu Sun;Xiaoning Qian
学习哈希已经成为流行的视频检索，由于其速度快，存储消耗低。以前的努力制定视频散列训练二进制自动编码器，其中非连续的潜在表示是由偏置直通（ST）反向传播启发式优化。我们建议将视频散列公式化为学习具有因子化Bernoulli潜在分布的离散变分自动编码器，称为Bernoulli变分自动编码器（BerVAE）。在我们的BerVAE实现中，相应的证据下限（ELBO）导致了封闭形式的梯度表达式，该表达式可以与其他一些无偏梯度估计器一起用于实现原则性训练沿着。BerVAE通过预测视频哈希码字的概率分布来实现不确定性感知的视频哈希，从而提供可靠的不确定性量化。仿真和真实世界的大规模视频数据的实验表明，我们的无偏梯度估计训练的BerVAE可以达到最先进的检索性能。此外，我们表明，量化的不确定性是高度相关的视频检索性能，这可以用来进一步提高检索精度。我们的代码可在
Learning to hash has become popular for video retrieval due to its fast speed and low storage consumption. Previous efforts formulate video hashing as training a binary auto-encoder, for which noncontinuous latent representations are optimized by the biased straight-through (ST) back-propagation heuristic. We propose to formulate video hashing as learning a discrete variational auto-encoder with the factorized Bernoulli latent distribution, termed as Bernoulli variational auto-encoder (BerVAE). The corresponding evidence lower bound (ELBO) in our BerVAE implementation leads to closed-form gradient expression, which can be applied to achieve principled training along with some other unbiased gradient estimators. BerVAE enables uncertainty-aware video hashing by predicting the probability distribution of video hash code-words, thus providing reliable uncertainty quantification. Experiments on both simulated and real-world large-scale video data demonstrate that our BerVAE trained with unbiased gradient estimators can achieve the state-of-the-art retrieval performance. Furthermore, we show that quantified uncertainty is highly correlated to video retrieval performance, which can be leveraged to further improve the retrieval accuracy. Our code is available at