Heterogeneous Domain Adaptation via Soft Transfer Network
This work addresses the problem of transferring knowledge across heterogeneous domains for machine learning practitioners, representing an incremental improvement with a novel soft-label strategy.
The paper tackles heterogeneous domain adaptation by proposing a Soft Transfer Network that aligns discriminative directions and matches marginal and conditional distributions to prevent negative transfer, achieving significant performance improvements over state-of-the-art methods in image-to-image, text-to-image, and text-to-text tasks.
Heterogeneous domain adaptation (HDA) aims to facilitate the learning task in a target domain by borrowing knowledge from a heterogeneous source domain. In this paper, we propose a Soft Transfer Network (STN), which jointly learns a domain-shared classifier and a domain-invariant subspace in an end-to-end manner, for addressing the HDA problem. The proposed STN not only aligns the discriminative directions of domains but also matches both the marginal and conditional distributions across domains. To circumvent negative transfer, STN aligns the conditional distributions by using the soft-label strategy of unlabeled target data, which prevents the hard assignment of each unlabeled target data to only one category that may be incorrect. Further, STN introduces an adaptive coefficient to gradually increase the importance of the soft-labels since they will become more and more accurate as the number of iterations increases. We perform experiments on the transfer tasks of image-to-image, text-to-image, and text-to-text. Experimental results testify that the STN significantly outperforms several state-of-the-art approaches.