Improving Anomaly Segmentation with Multi-Granularity Cross-Domain
Alignment
- URL: http://arxiv.org/abs/2308.08696v2
- Date: Mon, 16 Oct 2023 16:12:09 GMT
- Title: Improving Anomaly Segmentation with Multi-Granularity Cross-Domain
Alignment
- Authors: Ji Zhang, Xiao Wu, Zhi-Qi Cheng, Qi He, Wei Li
- Abstract summary: Anomaly segmentation plays a pivotal role in identifying atypical objects in images, crucial for hazard detection in autonomous driving systems.
While existing methods demonstrate noteworthy results on synthetic data, they often fail to consider the disparity between synthetic and real-world data domains.
We introduce the Multi-Granularity Cross-Domain Alignment framework, tailored to harmonize features across domains at both the scene and individual sample levels.
- Score: 17.086123737443714
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Anomaly segmentation plays a pivotal role in identifying atypical objects in
images, crucial for hazard detection in autonomous driving systems. While
existing methods demonstrate noteworthy results on synthetic data, they often
fail to consider the disparity between synthetic and real-world data domains.
Addressing this gap, we introduce the Multi-Granularity Cross-Domain Alignment
(MGCDA) framework, tailored to harmonize features across domains at both the
scene and individual sample levels. Our contributions are twofold: i) We
present the Multi-source Domain Adversarial Training module. This integrates a
multi-source adversarial loss coupled with dynamic label smoothing,
facilitating the learning of domain-agnostic representations across multiple
processing stages. ii) We propose an innovative Cross-domain Anomaly-aware
Contrastive Learning methodology.} This method adeptly selects challenging
anchor points and images using an anomaly-centric strategy, ensuring precise
alignment at the sample level. Extensive evaluations of the Fishyscapes and
RoadAnomaly datasets demonstrate MGCDA's superior performance and adaptability.
Additionally, its ability to perform parameter-free inference and function with
various network architectures highlights its distinctiveness in advancing the
frontier of anomaly segmentation.
Related papers
- Multisource Collaborative Domain Generalization for Cross-Scene Remote Sensing Image Classification [57.945437355714155]
Cross-scene image classification aims to transfer prior knowledge of ground materials to annotate regions with different distributions.
Existing approaches focus on single-source domain generalization to unseen target domains.
We propose a novel multi-source collaborative domain generalization framework (MS-CDG) based on homogeneity and heterogeneity characteristics of multi-source remote sensing data.
arXiv Detail & Related papers (2024-12-05T06:15:08Z) - Joint semi-supervised and contrastive learning enables domain generalization and multi-domain segmentation [1.5393913074555419]
We introduce SegCLR, a versatile framework designed to segment images across different domains.
SegCLR employs supervised and contrastive learning simultaneously to effectively learn from both labeled and unlabeled data.
We demonstrate the superior performance of SegCLR through a comprehensive evaluation involving three diverse clinical datasets.
arXiv Detail & Related papers (2024-05-08T18:10:59Z) - Unified Domain Adaptive Semantic Segmentation [96.74199626935294]
Unsupervised Adaptive Domain Semantic (UDA-SS) aims to transfer the supervision from a labeled source domain to an unlabeled target domain.
We propose a Quad-directional Mixup (QuadMix) method, characterized by tackling distinct point attributes and feature inconsistencies.
Our method outperforms the state-of-the-art works by large margins on four challenging UDA-SS benchmarks.
arXiv Detail & Related papers (2023-11-22T09:18:49Z) - Robust Domain Adaptive Object Detection with Unified Multi-Granularity Alignment [59.831917206058435]
Domain adaptive detection aims to improve the generalization of detectors on target domain.
Recent approaches achieve domain adaption through feature alignment in different granularities via adversarial learning.
We introduce a unified multi-granularity alignment (MGA)-based detection framework for domain-invariant feature learning.
arXiv Detail & Related papers (2023-01-01T08:38:07Z) - Multi-Granularity Alignment Domain Adaptation for Object Detection [33.32519045960187]
Domain adaptive object detection is challenging due to distinctive data distribution between source domain and target domain.
We propose a unified multi-granularity alignment based object detection framework towards domain-invariant feature learning.
arXiv Detail & Related papers (2022-03-31T09:05:06Z) - Consistency and Diversity induced Human Motion Segmentation [231.36289425663702]
We propose a novel Consistency and Diversity induced human Motion (CDMS) algorithm.
Our model factorizes the source and target data into distinct multi-layer feature spaces.
A multi-mutual learning strategy is carried out to reduce the domain gap between the source and target data.
arXiv Detail & Related papers (2022-02-10T06:23:56Z) - AFAN: Augmented Feature Alignment Network for Cross-Domain Object
Detection [90.18752912204778]
Unsupervised domain adaptation for object detection is a challenging problem with many real-world applications.
We propose a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training.
Our approach significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations.
arXiv Detail & Related papers (2021-06-10T05:01:20Z) - Towards Adaptive Semantic Segmentation by Progressive Feature Refinement [16.40758125170239]
We propose an innovative progressive feature refinement framework, along with domain adversarial learning to boost the transferability of segmentation networks.
As a result, the segmentation models trained with source domain images can be transferred to a target domain without significant performance degradation.
arXiv Detail & Related papers (2020-09-30T04:17:48Z) - MADAN: Multi-source Adversarial Domain Aggregation Network for Domain
Adaptation [58.38749495295393]
Domain adaptation aims to learn a transferable model to bridge the domain shift between one labeled source domain and another sparsely labeled or unlabeled target domain.
Recent multi-source domain adaptation (MDA) methods do not consider the pixel-level alignment between sources and target.
We propose a novel MDA framework to address these challenges.
arXiv Detail & Related papers (2020-02-19T21:22:00Z)
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.