arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.08618cs.CVcs.AI
收藏

相异空间中的图像检索方法

Image Retrieval Methods in the Dissimilarity Space

Delhi Technological University(德里理工大学)

Madhu Kiran, Kartikey Vishnu, Rafael M. O. Cruz, Eric Granger

AI总结:

针对欧氏空间匹配的性能局限,该研究提出在相异空间中通过二分变换生成单嵌入、结合正则化最大间隔分类器与骨干网络端到端训练的图像检索方法,实验验证其准确率更优。

摘要:

图像检索方法依赖度量学习来训练骨干特征提取模型,这类模型可提取具有判别性的查询特征与参考(图库)特征表示,用于相似度匹配。尽管随着在大规模数据集上训练的深度学习(DL)模型的出现,当前最优方法的准确率已大幅提升,但在许多现实世界的视频分析与监控应用(例如行人重识别)中,图像检索仍然颇具挑战。由于维数灾难、过拟合以及对噪声数据的敏感性,使用欧氏空间进行匹配限制了其在现实应用中的性能。\n我们认为特征相异空间更适合用于相似度匹配,并提出了一种二分变换,将查询嵌入与参考嵌入投影为相异空间中的单个嵌入。\n我们还主张对骨干模型与二元分类模型进行端到端训练,以实现成对匹配。与比较查询嵌入和参考嵌入之间的距离不同,我们证明了对单个相异空间嵌入进行分类(判定为相似或相异)的优势,尤其是在采用端到端训练的情况下。我们提出了一种方法,通过对分类器权重的L2范数施加约束并结合铰链损失,来联合训练最大间隔分类器与骨干特征提取器。\n我们在多个具有挑战性的图像检索数据集上、使用多种不同的特征提取骨干网络开展了大量实验,结果凸显了在相异空间中进行相似度匹配的优势。具体而言,当联合训练特征提取骨干网络与用于匹配的正则化分类器时,相异空间可实现更高水平的准确率。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑