Robust visual domain adaptation with low-rank reconstruction

Abstract

Visual domain adaptation addresses the problem of adapting the sample distribution of the source domain to the target domain, where the recognition task is intended but the data distributions are different. In this paper, we present a low-rank reconstruction method to reduce the domain distribution disparity. Specifically, we transform the visual samples in the source domain into an intermediate representation such that each transformed source sample can be linearly reconstructed by the samples of the target domain. Unlike the existing work, our method captures the intrinsic relatedness of the source samples during the adaptation process while uncovering the noises and outliers in the source domain that cannot be adapted, making it more robust than previous methods. We formulate our problem as a constrained nuclear norm and 2,1 norm minimization objective and then adopt the Augmented Lagrange Multiplier (ALM) method for the optimization. Extensive experiments on various visual adaptation tasks show that the proposed method consistently and significantly beats the state-of-theart domain adaptation methods.

High-performance zero-standby-power-consumption-under-bending pressure sensors for artificial reflex arc

“…Contrastive methods capture the semantic information of the samples by maximizing the lower bound of the mutual information between two augmented views (Kang et al, 2019b;Singh, 2021;Tang et al, 2021). In addition, reconstruction-based methods achieve alignment by carrying out source domain classification and reconstruction of target domain data or both source and target domain data (Ghifary et al, 2016;Jhuo et al, 2012). More discussion can be founded in existing review papers focusing on domain adaptation (Ramponi and Plank, 2020;Liu et al, 2022).…”

Minimising disparity in distribution for unsupervised domain adaptation by preserving the local spatial arrangement of data

“…Saenko et al [3,18] have calculated a transformation matrix such that the distance between instances in the same domain is minimised while that from different domains is maximised. The work published in [17,[19][20][21] have projected the original data from source and target domains to an optimal subspace, where the disparity between the two domains is minimised. Application of DA for improved results of object categorisation and video classification have also been discussed in [3,17,19,[22][23][24][25][26].…”

Feature Norm-Based Deep Network for Multi-Domain Fashion Image Retrieval

“…To mitigate the generalization bottleneck and bridge different distributions, extensive studies have been conducted on DA. 12,34–38 Some existing approaches 39,40 attempted to align feature spaces by exploiting shift-invariant information to match the target domain with the source domain. Meanwhile, from the perspective of deep learning, some methods 18,22,41–44 adopted Maximum Mean Discrepancy (MMD) and association-based losses.…”

“…To mitigate the generalization bottleneck and bridge different distributions, extensive studies have been conducted on DA. 12,[34][35][36][37][38] Some existing approaches 39,40 attempted to align feature spaces by exploiting shift-invariant information to match the target domain with the source domain.…”