Unsupervised Domain Adaptation in the Dissimilarity Space for Person
Re-identification
- URL: http://arxiv.org/abs/2007.13890v1
- Date: Mon, 27 Jul 2020 22:10:46 GMT
- Title: Unsupervised Domain Adaptation in the Dissimilarity Space for Person
Re-identification
- Authors: Djebril Mekhazni, Amran Bhuiyan, George Ekladious and Eric Granger
- Abstract summary: We propose a novel Dissimilarity-based Maximum Mean Discrepancy (D-MMD) loss for aligning pair-wise distances.
Empirical results with three challenging benchmark datasets show that the proposed D-MMD loss decreases as source and domain distributions become more similar.
- Score: 11.045405206338486
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Person re-identification (ReID) remains a challenging task in many real-word
video analytics and surveillance applications, even though state-of-the-art
accuracy has improved considerably with the advent of deep learning (DL) models
trained on large image datasets. Given the shift in distributions that
typically occurs between video data captured from the source and target
domains, and absence of labeled data from the target domain, it is difficult to
adapt a DL model for accurate recognition of target data. We argue that for
pair-wise matchers that rely on metric learning, e.g., Siamese networks for
person ReID, the unsupervised domain adaptation (UDA) objective should consist
in aligning pair-wise dissimilarity between domains, rather than aligning
feature representations. Moreover, dissimilarity representations are more
suitable for designing open-set ReID systems, where identities differ in the
source and target domains. In this paper, we propose a novel
Dissimilarity-based Maximum Mean Discrepancy (D-MMD) loss for aligning
pair-wise distances that can be optimized via gradient descent. From a person
ReID perspective, the evaluation of D-MMD loss is straightforward since the
tracklet information allows to label a distance vector as being either
within-class or between-class. This allows approximating the underlying
distribution of target pair-wise distances for D-MMD loss optimization, and
accordingly align source and target distance distributions. Empirical results
with three challenging benchmark datasets show that the proposed D-MMD loss
decreases as source and domain distributions become more similar. Extensive
experimental evaluation also indicates that UDA methods that rely on the D-MMD
loss can significantly outperform baseline and state-of-the-art UDA methods for
person ReID without the common requirement for data augmentation and/or complex
networks.
Related papers
- CMDA: Cross-Modal and Domain Adversarial Adaptation for LiDAR-Based 3D
Object Detection [14.063365469339812]
LiDAR-based 3D Object Detection methods often do not generalize well to target domains outside the source (or training) data distribution.
We introduce a novel unsupervised domain adaptation (UDA) method, called CMDA, which leverages visual semantic cues from an image modality.
We also introduce a self-training-based learning strategy, wherein a model is adversarially trained to generate domain-invariant features.
arXiv Detail & Related papers (2024-03-06T14:12:38Z) - Subject-Based Domain Adaptation for Facial Expression Recognition [51.10374151948157]
Adapting a deep learning model to a specific target individual is a challenging facial expression recognition task.
This paper introduces a new MSDA method for subject-based domain adaptation in FER.
It efficiently leverages information from multiple source subjects to adapt a deep FER model to a single target individual.
arXiv Detail & Related papers (2023-12-09T18:40:37Z) - Divide and Contrast: Source-free Domain Adaptation via Adaptive
Contrastive Learning [122.62311703151215]
Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations.
DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals.
We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
arXiv Detail & Related papers (2022-11-12T09:21:49Z) - Deep Unsupervised Domain Adaptation: A Review of Recent Advances and
Perspectives [16.68091981866261]
Unsupervised domain adaptation (UDA) is proposed to counter the performance drop on data in a target domain.
UDA has yielded promising results on natural image processing, video analysis, natural language processing, time-series data analysis, medical image analysis, etc.
arXiv Detail & Related papers (2022-08-15T20:05:07Z) - Learning Feature Decomposition for Domain Adaptive Monocular Depth
Estimation [51.15061013818216]
Supervised approaches have led to great success with the advance of deep learning, but they rely on large quantities of ground-truth depth annotations.
Unsupervised domain adaptation (UDA) transfers knowledge from labeled source data to unlabeled target data, so as to relax the constraint of supervised learning.
We propose a novel UDA method for MDE, referred to as Learning Feature Decomposition for Adaptation (LFDA), which learns to decompose the feature space into content and style components.
arXiv Detail & Related papers (2022-07-30T08:05:35Z) - Instance Relation Graph Guided Source-Free Domain Adaptive Object
Detection [79.89082006155135]
Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift.
UDA methods try to align the source and target representations to improve the generalization on the target domain.
The Source-Free Adaptation Domain (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data.
arXiv Detail & Related papers (2022-03-29T17:50:43Z) - Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains.
We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
arXiv Detail & Related papers (2021-12-12T06:11:16Z) - Stagewise Unsupervised Domain Adaptation with Adversarial Self-Training
for Road Segmentation of Remote Sensing Images [93.50240389540252]
Road segmentation from remote sensing images is a challenging task with wide ranges of application potentials.
We propose a novel stagewise domain adaptation model called RoadDA to address the domain shift (DS) issue in this field.
Experiment results on two benchmarks demonstrate that RoadDA can efficiently reduce the domain gap and outperforms state-of-the-art methods.
arXiv Detail & Related papers (2021-08-28T09:29:14Z) - Source-Free Domain Adaptation for Semantic Segmentation [11.722728148523366]
Unsupervised Domain Adaptation (UDA) can tackle the challenge that convolutional neural network-based approaches for semantic segmentation heavily rely on the pixel-level annotated data.
We propose a source-free domain adaptation framework for semantic segmentation, namely SFDA, in which only a well-trained source model and an unlabeled target domain dataset are available for adaptation.
arXiv Detail & Related papers (2021-03-30T14:14:29Z) - Adapt Everywhere: Unsupervised Adaptation of Point-Clouds and Entropy
Minimisation for Multi-modal Cardiac Image Segmentation [10.417009344120917]
We present a novel UDA method for multi-modal cardiac image segmentation.
The proposed method is based on adversarial learning and adapts network features between source and target domain in different spaces.
We validated our method on two cardiac datasets by adapting from the annotated source domain to the unannotated target domain.
arXiv Detail & Related papers (2021-03-15T08:59:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.