Abstract
Image retrieval methods rely on metric learning to train backbone feature extraction models that can extract discriminant queries and reference (gallery) feature representations for similarity matching. Although state-of-the-art accuracy has improved considerably with the advent of deep learning (DL) models trained on large datasets, image retrieval remains challenging in many real-world video analytics and surveillance applications, e.g., person re-identification. Using the Euclidean space for matching limits the performance in real-world applications due to the curse of dimensionality, overfitting, and sensitivity to noisy data. We argue that the feature dissimilarity space is more suitable for similarity matching, and propose a dichotomy transformation to project query and reference embeddings into a single embedding in the dissimilarity space. We also advocate for end-to-end training of a backbone and binary classification models for pair-wise matching. As opposed to comparing the distance between queries and reference embeddings, we show the benefits of classifying the single dissimilarity space embedding (as similar or dissimilar), especially when trained end-to-end. We propose a method to train the max-margin classifier together with the backbone feature extractor by applying constraints to the L2 norm of the classifier weights along with the hinge loss. Our extensive experiments on challenging image retrieval datasets and using diverse feature extraction backbones highlight the benefits of similarity matching in the dissimilarity space. In particular, when jointly training the feature extraction backbone and regularised classifier for matching, the dissimilarity space provides a higher level of accuracy.
Abstract (translated)
图像检索方法依赖度量学习来训练骨干特征提取模型，该模型能够抽取具有判别力的查询和参考（画廊）特征表示以进行相似性匹配。尽管随着深度学习(DL)模型在大规模数据集上的应用，状态-of-the-art准确率有了显著提高，但在许多实际视频分析和监控应用场景中，如行人重识别，图像检索仍然是一项挑战。使用欧几里得空间进行匹配由于维度灾难、过拟合以及对噪声数据的敏感性限制了其在实际应用中的性能表现。我们认为特征不相似空间更适合于相似性匹配，并提出了一种二分转换方法，将查询和参考嵌入投影到单个不相似度空间中的单一嵌入中。我们还提倡端到端训练骨干模型与用于配对匹配的二元分类模型。通过分类单个不相似度空间嵌入（将其归类为相似或不相似），而不是比较查询和参考嵌入之间的距离，尤其是在进行端到端训练时，能够展示出显著的好处。我们提出了一种方法，通过对分类器权重施加L2范数约束以及结合铰链损失来同时训练最大间隔分类器与骨干特征提取器。我们在具有挑战性的图像检索数据集上的广泛实验及使用各种特征提取骨干模型均表明，在不相似度空间中进行相似性匹配的优势。特别是，当联合训练特征提取骨干和正则化分类器时，不相似度空间提供了更高的准确率水平。
URL
https://arxiv.org/abs/2412.08618
