An autoassociative memory model is a function that, given a set of data points, takes as input an arbitrary vector and outputs the most similar data point from the memorized set. However, popular memory models fail to retrieve images even when the corruption is mild and easy to detect for a human evaluator. This is because similarities are evaluated in the raw pixel space, which does not contain any semantic information about the images. This problem can be easily solved by computing \emph{similarities} in an embedding space instead of the pixel space. We show that an effective way of computing such embeddings is via a network pretrained with a contrastive loss. As the dimension of embedding spaces is often significantly smaller than the pixel space, we also have a faster computation of similarity scores. We test this method on complex datasets such as CIFAR10 and STL10. An additional drawback of current models is the need of storing the whole dataset in the pixel space, which is often extremely large. We relax this condition and propose a class of memory models that only stores low-dimensional semantic embeddings, and uses them to retrieve similar, but not identical, memories. We demonstrate a proof of concept of this method on a simple task on the MNIST dataset.

翻译：自联想记忆模型是一种函数：给定一组数据点，该模型以任意向量为输入，输出记忆集中与输入最相似的数据点。然而，现有的记忆模型即使在图像失真轻微且人类评估者易于察觉的简单场景下，也常无法成功检索图像。其根本原因在于相似性评估发生在原始像素空间中，该空间不包含任何图像的语义信息。这一难题可通过在嵌入空间而非像素空间计算相似性轻松解决。我们证明，通过采用对比损失预训练的神经网络是计算此类嵌入的有效方式。由于嵌入空间维度通常显著小于像素空间，相似性分数的计算速度也得到提升。我们在CIFAR10和STL10等复杂数据集上测试了该方法。当前模型的另一个缺陷是需要存储整个数据集的像素空间表示，这往往导致存储需求极其庞大。我们放宽了这一条件，提出一类仅存储低维语义嵌入的记忆模型，并利用这些嵌入检索相似但非完全相同的记忆。我们通过在MNIST数据集上的简单任务验证了该方法的可行性。