Multiclass transfer learning from unconstrained priors
Multiclass transfer learning from unconstrained priors
复制标题
DOI：
10.1109/iccv.2011.6126454
复制
发表时间：
2011-11
期刊：
影响因子：
--
通讯作者：
Jie Luo;T. Tommasi;B. Caputo
中科院分区：
文献类型：
--
作者：
Jie Luo;T. Tommasi;B. Caputo
在过去几年中，视觉识别领域提出的绝大多数迁移学习方法都解决了对象类别检测的问题，假设对进行迁移的先验知识有很强的控制。这是一个严格的条件，因为它具体限制了在若干情况下使用这类方法：例如，它一般不允许使用现成的模型作为先验。此外，大多数现有迁移学习算法缺乏多类公式，这阻碍了将它们用于对象分类问题，在这些问题上，它们的使用可能是有益的，特别是当类别数量增加并且更难获得足够的注释数据来训练标准时。学习方法。本文提出了一种多类迁移学习算法，该算法允许利用建立在不同特征上的先验知识，并使用与用于学习新任务的学习方法不同的学习方法。我们使用先验作为专家，并将其输出作为附加信息传递给新的传入样本。我们在多核学习框架内投射学习问题。由此产生的配方有效地解决了一个联合优化问题，确定从哪里和多少转移，与原则性的多类配方。大量的实验证明了这种方法的价值。
The vast majority of transfer learning methods proposed in the visual recognition domain over the last years addresses the problem of object category detection, assuming a strong control over the priors from which transfer is done. This is a strict condition, as it concretely limits the use of this type of approach in several settings: for instance, it does not allow in general to use off-the-shelf models as priors. Moreover, the lack of a multiclass formulation for most of the existing transfer learning algorithms prevents using them for object categorization problems, where their use might be beneficial, especially when the number of categories grows and it becomes harder to get enough annotated data for training standard learning methods. This paper presents a multiclass transfer learning algorithm that allows to take advantage of priors built over different features and with different learning methods than the one used for learning the new task. We use the priors as experts, and transfer their outputs to the new incoming samples as additional information. We cast the learning problem within the Multi Kernel Learning framework. The resulting formulation solves efficiently a joint optimization problem that determines from where and how much to transfer, with a principled multiclass formulation. Extensive experiments illustrate the value of this approach.