基于特定领域成对图像比较的快速概率兴趣学习
Rapid Probabilistic Interest Learning from Domain-Specific Pairwise Image Comparisons
摘要：
大量的工作旨在发现用于视觉搜索和信息检索的图像兴趣或可记忆性的大型通用模型。本文认为，图像的兴趣往往是领域和用户特定的，有效的机制，了解这个特定领域的图像兴趣尽快，同时限制所需的数据标签的数量，往往是更有用的最终用户。这项工作使用成对图像比较来减少这些用户的标签负担，并引入了一种图像兴趣估计方法，该方法与最近使用成对排名损失训练的数据饥渴深度学习方法类似。在这里，我们使用一个高斯过程模型来插值图像的兴趣推断使用贝叶斯排名的方法在使用预训练的卷积神经网络提取的图像特征。结果表明，在高维图像特征空间中拟合高斯过程不仅在计算上是可行的，而且在广泛的领域中也是有效的。所提出的概率兴趣估计方法产生与不确定性配对的图像兴趣，这些不确定性可用于识别需要额外标记的图像并测量推理收敛，从而允许样本有效的主动模型训练。重要的是，概率公式允许有效的视觉搜索和信息检索时，有限的标签数据是可用的。
英文摘要：
A great deal of work aims to discover large general purpose models of image interest or memorability for visual search and information retrieval. This paper argues that image interest is often domain and user specific, and that efficient mechanisms for learning about this domain-specific image interest as quickly as possible, while limiting the amount of data-labelling required, are often more useful to end-users. This work uses pairwise image comparisons to reduce the labelling burden on these users, and introduces an image interest estimation approach that performs similarly to recent data hungry deep learning approaches trained using pairwise ranking losses. Here, we use a Gaussian process model to interpolate image interest inferred using a Bayesian ranking approach over image features extracted using a pre-trained convolutional neural network. Results show that fitting a Gaussian process in high-dimensional image feature space is not only computationally feasible, but also effective across a broad range of domains. The proposed probabilistic interest estimation approach produces image interests paired with uncertainties that can be used to identify images for which additional labelling is required and measure inference convergence, allowing for sample efficient active model training. Importantly, the probabilistic formulation allows for effective visual search and information retrieval when limited labelling data is available.
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。
