MIDAS: Modeling Ground-Truth Distributions with Dark Knowledge for Domain Generalized Stereo Matching

• URL: http://arxiv.org/abs/2503.04376v1
• Date: Thu, 06 Mar 2025 12:27:58 GMT
• Title: MIDAS: Modeling Ground-Truth Distributions with Dark Knowledge for Domain Generalized Stereo Matching
• Authors: Peng Xu, Zhiyu Xiang, Jingyun Fu, Tianyu Pu, Hanzhi Zhong, Eryun Liu,
• Abstract summary: We show that PCWNet with our method achieves the state-of-the-art generalization performance on KITTI 2015 and 2012 datasets.<n>Our method outperforms existing methods in comprehensive ranking across four popular real-world datasets.
• Score: 7.710350925846268
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the significant advances in domain generalized stereo matching, existing methods still exhibit domain-specific preferences when transferring from synthetic to real domains, hindering their practical applications in complex and diverse scenarios. The probability distributions predicted by the stereo network naturally encode rich similarity and uncertainty information. Inspired by this observation, we propose to extract these two types of dark knowledge from the pre-trained network to model intuitive multi-modal ground-truth distributions for both edge and non-edge regions. To mitigate the inherent domain preferences of a single network, we adopt network ensemble and further distinguish between objective and biased knowledge in the Laplace parameter space. Finally, the objective knowledge and the original disparity labels are jointly modeled as a mixture of Laplacians to provide fine-grained supervision for the stereo network training. Extensive experiments demonstrate that: 1) Our method is generic and effectively improves the generalization of existing networks. 2) PCWNet with our method achieves the state-of-the-art generalization performance on both KITTI 2015 and 2012 datasets. 3) Our method outperforms existing methods in comprehensive ranking across four popular real-world datasets.

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)
• Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts [56.57141696245328]
  In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety. Existing methods often struggle to distinguish between domain-level and semantic-level distribution shifts.
  arXiv  Detail & Related papers  (2024-11-06T11:03:02Z)
• MADOD: Generalizing OOD Detection to Unseen Domains via G-Invariance Meta-Learning [10.38552112657656]
  We introduce Meta-learned Across Domain Out-of-distribution Detection (MADOD), a novel framework designed to address both shifts concurrently. Our key innovation lies in task construction: we randomly designate in-distribution classes as pseudo-OODs within each meta-learning task. Experiments on real-world and synthetic datasets demonstrate MADOD's superior performance in semantic OOD detection across unseen domains.
  arXiv  Detail & Related papers  (2024-11-02T17:46:23Z)
• Uncertainty-guided Contrastive Learning for Single Source Domain Generalisation [15.907643838530655]
  In this paper, we introduce a novel model referred to as Contrastive Uncertainty Domain Generalisation Network (CUDGNet) The key idea is to augment the source capacity in both input and label spaces through the fictitious domain generator. Our method also provides efficient uncertainty estimation at inference time from a single forward pass through the generator subnetwork.
  arXiv  Detail & Related papers  (2024-03-12T10:47:45Z)
• Improving Intrusion Detection with Domain-Invariant Representation Learning in Latent Space [4.871119861180455]
  We introduce a two-phase representation learning technique using multi-task learning. We disentangle the latent space by minimizing the mutual information between the prior and latent space. We assess the model's efficacy across multiple cybersecurity datasets.
  arXiv  Detail & Related papers  (2023-12-28T17:24:13Z)
• The Open-World Lottery Ticket Hypothesis for OOD Intent Classification [68.93357975024773]
  We shed light on the fundamental cause of model overconfidence on OOD. We also extend the Lottery Ticket Hypothesis to open-world scenarios.
  arXiv  Detail & Related papers  (2022-10-13T14:58:35Z)
• TAL: Two-stream Adaptive Learning for Generalizable Person Re-identification [115.31432027711202]
  We argue that both domain-specific and domain-invariant features are crucial for improving the generalization ability of re-id models. We name two-stream adaptive learning (TAL) to simultaneously model these two kinds of information. Our framework can be applied to both single-source and multi-source domain generalization tasks.
  arXiv  Detail & Related papers  (2021-11-29T01:27:42Z)
• WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentation [72.88657378658549]
  We propose a WEb-image assisted Domain GEneralization scheme, which is the first to exploit the diversity of web-crawled images for generalizable semantic segmentation. We also present a method which injects styles of the web-crawled images into training images on-the-fly during training, which enables the network to experience images of diverse styles with reliable labels for effective training.
  arXiv  Detail & Related papers  (2021-09-29T05:19:58Z)
• Coarse to Fine: Domain Adaptive Crowd Counting via Adversarial Scoring Network [58.05473757538834]
  This paper proposes a novel adversarial scoring network (ASNet) to bridge the gap across domains from coarse to fine granularity. Three sets of migration experiments show that the proposed methods achieve state-of-the-art counting performance.
  arXiv  Detail & Related papers  (2021-07-27T14:47:24Z)
• A Bit More Bayesian: Domain-Invariant Learning with Uncertainty [111.22588110362705]
  Domain generalization is challenging due to the domain shift and the uncertainty caused by the inaccessibility of target domain data. In this paper, we address both challenges with a probabilistic framework based on variational Bayesian inference. We derive domain-invariant representations and classifiers, which are jointly established in a two-layer Bayesian neural network.
  arXiv  Detail & Related papers  (2021-05-09T21:33:27Z)
• A Multi-Semantic Metapath Model for Large Scale Heterogeneous Network Representation Learning [52.83948119677194]
  We propose a multi-semantic metapath (MSM) model for large scale heterogeneous representation learning. Specifically, we generate multi-semantic metapath-based random walks to construct the heterogeneous neighborhood to handle the unbalanced distributions. We conduct systematical evaluations for the proposed framework on two challenging datasets: Amazon and Alibaba.
  arXiv  Detail & Related papers  (2020-07-19T22:50:20Z)
• Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training [22.366638308792734]
  Unsupervised Domain Adaptation (UDA) aims at improving the generalization capability of a model trained on a source domain to perform well on a target domain for which no labeled data is available. We propose an approach to adapt a deep neural network trained on synthetic data to real scenes addressing the domain shift between the two different data distributions.
  arXiv  Detail & Related papers  (2020-04-27T11:48:03Z)

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.