Domain-Agnostic Prior for Transfer Semantic Segmentation
- URL: http://arxiv.org/abs/2204.02684v1
- Date: Wed, 6 Apr 2022 09:13:25 GMT
- Title: Domain-Agnostic Prior for Transfer Semantic Segmentation
- Authors: Xinyue Huo, Lingxi Xie, Hengtong Hu, Wengang Zhou, Houqiang Li, Qi
Tian
- Abstract summary: Unsupervised domain adaptation (UDA) is an important topic in the computer vision community.
We present a mechanism that regularizes cross-domain representation learning with a domain-agnostic prior (DAP)
Our research reveals that UDA benefits much from better proxies, possibly from other data modalities.
- Score: 197.9378107222422
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Unsupervised domain adaptation (UDA) is an important topic in the computer
vision community. The key difficulty lies in defining a common property between
the source and target domains so that the source-domain features can align with
the target-domain semantics. In this paper, we present a simple and effective
mechanism that regularizes cross-domain representation learning with a
domain-agnostic prior (DAP) that constrains the features extracted from source
and target domains to align with a domain-agnostic space. In practice, this is
easily implemented as an extra loss term that requires a little extra costs. In
the standard evaluation protocol of transferring synthesized data to real data,
we validate the effectiveness of different types of DAP, especially that
borrowed from a text embedding model that shows favorable performance beyond
the state-of-the-art UDA approaches in terms of segmentation accuracy. Our
research reveals that UDA benefits much from better proxies, possibly from
other data modalities.
Related papers
- Style Adaptation for Domain-adaptive Semantic Segmentation [2.1365683052370046]
Domain discrepancy leads to a significant decrease in the performance of general network models trained on the source domain data when applied to the target domain.
We introduce a straightforward approach to mitigate the domain discrepancy, which necessitates no additional parameter calculations and seamlessly integrates with self-training-based UDA methods.
Our proposed method attains a noteworthy UDA performance of 76.93 mIoU on the GTA->Cityscapes dataset, representing a notable improvement of +1.03 percentage points over the previous state-of-the-art results.
arXiv Detail & Related papers (2024-04-25T02:51:55Z) - Source-Free Domain Adaptation for Medical Image Segmentation via
Prototype-Anchored Feature Alignment and Contrastive Learning [57.43322536718131]
We present a two-stage source-free domain adaptation (SFDA) framework for medical image segmentation.
In the prototype-anchored feature alignment stage, we first utilize the weights of the pre-trained pixel-wise classifier as source prototypes.
Then, we introduce the bi-directional transport to align the target features with class prototypes by minimizing its expected cost.
arXiv Detail & Related papers (2023-07-19T06:07:12Z) - Towards Source-free Domain Adaptive Semantic Segmentation via Importance-aware and Prototype-contrast Learning [26.544837987747766]
We propose an end-to-end source-free domain adaptation semantic segmentation method via Importance-Aware and Prototype-Contrast learning.
The proposed IAPC framework effectively extracts domain-invariant knowledge from the well-trained source model and learns domain-specific knowledge from the unlabeled target domain.
arXiv Detail & Related papers (2023-06-02T15:09:19Z) - AVATAR: Adversarial self-superVised domain Adaptation network for TARget
domain [11.764601181046496]
This paper presents an unsupervised domain adaptation (UDA) method for predicting unlabeled target domain data.
We propose the Adversarial self-superVised domain Adaptation network for the TARget domain (AVATAR) algorithm.
Our proposed model significantly outperforms state-of-the-art methods on three UDA benchmarks.
arXiv Detail & Related papers (2023-04-28T20:31:56Z) - ConDA: Unsupervised Domain Adaptation for LiDAR Segmentation via
Regularized Domain Concatenation [10.65673380743972]
ConDA is a concatenation-based domain adaptation framework for LiDAR segmentation.
We propose an anti-aliasing regularizer and an entropy aggregator to reduce the negative effect caused by the aliasing artifacts and noisy pseudo labels.
arXiv Detail & Related papers (2021-11-30T09:53:24Z) - Instance Level Affinity-Based Transfer for Unsupervised Domain
Adaptation [74.71931918541748]
We propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA.
We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process.
We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets.
arXiv Detail & Related papers (2021-04-03T01:33:14Z) - Disentanglement-based Cross-Domain Feature Augmentation for Effective
Unsupervised Domain Adaptive Person Re-identification [87.72851934197936]
Unsupervised domain adaptive (UDA) person re-identification (ReID) aims to transfer the knowledge from the labeled source domain to the unlabeled target domain for person matching.
One challenge is how to generate target domain samples with reliable labels for training.
We propose a Disentanglement-based Cross-Domain Feature Augmentation strategy.
arXiv Detail & Related papers (2021-03-25T15:28:41Z) - Heuristic Domain Adaptation [105.59792285047536]
Heuristic Domain Adaptation Network (HDAN) explicitly learns the domain-invariant and domain-specific representations.
Heuristic Domain Adaptation Network (HDAN) has exceeded state-of-the-art on unsupervised DA, multi-source DA and semi-supervised DA.
arXiv Detail & Related papers (2020-11-30T04:21:35Z) - Domain Conditioned Adaptation Network [90.63261870610211]
We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism.
This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
arXiv Detail & Related papers (2020-05-14T04:23:24Z)
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.