Despite significant recent advances in similarity detection tasks, existing
approaches pose substantial challenges under memory constraints. One of the
primary reasons for this is the use of computationally expensive metric
learning loss functions such as Triplet Loss in Siamese networks. In this
paper, we present a novel loss function called Shadow Loss that compresses the
dimensions of an embedding space during loss calculation without loss of
performance. The distance between the projections of the embeddings is learned
from inputs on a compact projection space where distances directly correspond
to a measure of class similarity. Projecting on a lower-dimension projection
space, our loss function converges faster, and the resulting classified image
clusters have higher inter-class and smaller intra-class distances. Shadow Loss
not only reduces embedding dimensions favoring memory constraint devices but
also consistently performs better than the state-of-the-art Triplet Margin Loss
by an accuracy of 5\%-10\% across diverse datasets. The proposed loss function
is also model agnostic, upholding its performance across several tested models.
Its effectiveness and robustness across balanced, imbalanced, medical, and
non-medical image datasets suggests that it is not specific to a particular
model or dataset but demonstrates superior performance consistently while using
less memory and computation.

提出了一种名为 Shadow Loss 的新型损失函数，通过在损失计算期间压缩嵌入空间的维度，从而在不损失性能的情况下克服了现有方法在内存限制下面临的挑战。该损失函数通过在紧凑投影空间上从输入中学习嵌入的投影之间的距离，这些距离直接对应于类相似性的度量。通过投影到低维投影空间，我们的损失函数收敛更快，并且所得到的分类图像聚类具有更高的类间距离和更小的类内距离。与现有技术 Triplet Margin Loss 相比，Shadow Loss 不仅能降低嵌入维度以适应内存受限设备，还能在各种不同的数据集上稳定地表现出 5%-10% 的准确度提升。该提议的损失函数与模型无关，在多个经过测试的模型上表现良好。在平衡、不平衡、医学和非医学图像数据集上的有效性和鲁棒性表明，它不特定于特定的模型或数据集，而是始终表现出卓越的性能，并且使用更少的内存和计算资源。