1st Place Solution to NeurIPS 2022 Challenge on Visual Domain Adaptation

• URL: http://arxiv.org/abs/2211.14596v1
• Date: Sat, 26 Nov 2022 15:45:31 GMT
• Title: 1st Place Solution to NeurIPS 2022 Challenge on Visual Domain Adaptation
• Authors: Daehan Kim, Minseok Seo, YoungJin Jeon, Dong-Geol Choi
• Abstract summary: We introduce the SIA_Adapt method, which incorporates several methods for domain adaptive models. Our method achieves 1st place in the VisDA2022 challenge.
• Score: 4.06040510836545
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Visual Domain Adaptation(VisDA) 2022 Challenge calls for an unsupervised domain adaptive model in semantic segmentation tasks for industrial waste sorting. In this paper, we introduce the SIA_Adapt method, which incorporates several methods for domain adaptive models. The core of our method in the transferable representation from large-scale pre-training. In this process, we choose a network architecture that differs from the state-of-the-art for domain adaptation. After that, self-training using pseudo-labels helps to make the initial adaptation model more adaptable to the target domain. Finally, the model soup scheme helped to improve the generalization performance in the target domain. Our method SIA_Adapt achieves 1st place in the VisDA2022 challenge. The code is available on https: //github.com/DaehanKim-Korea/VisDA2022_Winner_Solution.

Related papers

• Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation [84.82153655786183]
  We propose a novel framework called Informative Data Mining (IDM) to enable efficient one-shot domain adaptation for semantic segmentation. IDM provides an uncertainty-based selection criterion to identify the most informative samples, which facilitates quick adaptation and reduces redundant training. Our approach outperforms existing methods and achieves a new state-of-the-art one-shot performance of 56.7%/55.4% on the GTA5/SYNTHIA to Cityscapes adaptation tasks.
  arXiv  Detail & Related papers  (2023-09-25T15:56:01Z)
• AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models [127.04370753583261]
  Pretrained language models (PLMs) are trained on massive corpora, but often need to specialize to specific domains. A solution is to use a related-domain adapter for the novel domain at test time. We introduce AdapterSoup, an approach that performs weight-space averaging of adapters trained on different domains.
  arXiv  Detail & Related papers  (2023-02-14T13:09:23Z)
• UDApter -- Efficient Domain Adaptation Using Adapters [29.70751969196527]
  We propose two methods to make unsupervised domain adaptation more parameter efficient. The first method deconstructs UDA into a two-step process: first by adding a domain adapter to learn domain-invariant information. We are within 0.85% F1 for natural language inference task, by fine-tuning only a fraction of the full model parameters.
  arXiv  Detail & Related papers  (2023-02-07T02:04:17Z)
• Continual Unsupervised Domain Adaptation for Semantic Segmentation using a Class-Specific Transfer [9.46677024179954]
  segmentation models do not generalize to unseen domains. We propose a light-weight style transfer framework that incorporates two class-conditional AdaIN layers. We extensively validate our approach on a synthetic sequence and further propose a challenging sequence consisting of real domains.
  arXiv  Detail & Related papers  (2022-08-12T21:30:49Z)
• Target and Task specific Source-Free Domain Adaptive Image Segmentation [73.78898054277538]
  We propose a two-stage approach for source-free domain adaptive image segmentation. We focus on generating target-specific pseudo labels while suppressing high entropy regions. In the second stage, we focus on adapting the network for task-specific representation.
  arXiv  Detail & Related papers  (2022-03-29T17:50:22Z)
• 2nd Place Solution for VisDA 2021 Challenge -- Universally Domain Adaptive Image Recognition [38.54810374543916]
  We introduce a universal domain adaptation (UniDA) method by aggregating several popular feature extraction and domain adaptation schemes. As shown in the leaderboard, our proposed UniDA method ranks the 2nd place with 48.56% ACC and 70.72% AUROC in the VisDA 2021 Challenge.
  arXiv  Detail & Related papers  (2021-10-27T07:48:29Z)
• 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)
• Gradient Regularized Contrastive Learning for Continual Domain Adaptation [86.02012896014095]
  We study the problem of continual domain adaptation, where the model is presented with a labelled source domain and a sequence of unlabelled target domains. We propose Gradient Regularized Contrastive Learning (GRCL) to solve the obstacles. Experiments on Digits, DomainNet and Office-Caltech benchmarks demonstrate the strong performance of our approach.
  arXiv  Detail & Related papers  (2021-03-23T04:10:42Z)
• 1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification [17.065458476210175]
  This paper presents our proposed methods for domain adaptive pedestrian re-identification (Re-ID) task in Visual Domain Adaptation Challenge (VisDA-2020) Considering the large gap between the source domain and target domain, we focused on solving two biases that influenced the performance on domain adaptive pedestrian Re-ID. Our methods achieve 76.56% mAP and 84.25% rank-1 on the test set.
  arXiv  Detail & Related papers  (2020-12-25T03:02:46Z)
• Supervised Domain Adaptation using Graph Embedding [86.3361797111839]
  Domain adaptation methods assume that distributions between the two domains are shifted and attempt to realign them. We propose a generic framework based on graph embedding. We show that the proposed approach leads to a powerful Domain Adaptation framework.
  arXiv  Detail & Related papers  (2020-03-09T12:25:13Z)

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.