# [2011.00147] Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentationopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

Domain adaptive semantic segmentation aims to train a model performing satisfactory pixel-level predictions on the target with only out-of-domain (source) annotations. The conventional solution to this task is to minimize the discrepancy between source and target to enable effective knowledge transfer. Previous domain discrepancy minimization methods are mainly based on the adversarial training. They tend to consider the domain discrepancy globally, which ignore the pixel-wise relationships and are less discriminative. In this paper, we propose to build the pixel-level cycle association between source and target pixel pairs and contrastively strengthen their connections to diminish the domain gap and make the features more discriminative. To the best of our knowledge, this is a new perspective for tackling such a challenging task. Experiment results on two representative domain adaptation benchmarks, i.e. GTAV $\rightarrow$ Cityscapes and SYNTHIA $\rightarrow$ Cityscapes, verify the ef

2 mentions:
Keywords:
Date:

## Referring Tweets

@AkiraTOSEI t.co/yVX8HAoCYA 領域分割タスクにおいて、ランダム抽出したsourceパッチ→その最近傍targetパッチ→その最近傍sourceパッチのラベルが同じものになるように制約をかけることで、ドメイン適応を行う研究。先行研究を大きく超える結果。 t.co/6Vl5Cju4PF
@AkiraTOSEI t.co/yVX8HAoCYA A study of domain adaptation in semantic segmentation task by constraining the labels of randomly extracted source patches >its nearest neighbor target patches >its nearest neighbor source patches to be the same. The results greatly exceed previous results t.co/cnjBOVAkmx

## Related Entries

[2006.10337] Category-Specific CNN for Visual-aware CTR Prediction at JD.comopen searchopen navigati...
0 users, 2 mentions 2020/11/12 12:59
[2012.00364] Pre-Trained Image Processing Transformer
0 users, 2 mentions 2020/12/23 11:21
[2012.06044] Mesoscopic photogrammetry with an unstabilized phone camera
0 users, 2 mentions 2020/12/25 17:21
[2010.04456] Augmenting Physical Models with Deep Networks for Complex Dynamics Forecasting
0 users, 2 mentions 2021/02/12 11:21
MAE/SimMIM for Pre-Training Like a Masked Language Model | by Akihiro FUJII | Dec, 2021 | Medium
0 users, 1 mentions 2021/12/23 22:09

# ML-Newsについて

ML-NewsはSNSを情報源とした機械学習に特化したニュースサイトです。機械学習に関する論文ブログライブラリコンペティション発表資料勉強会などの最新の情報を効率的に収集できます。

## お知らせ

• 2021/12/31: デザインを刷新しました
• 2021/04/08: 日本語Kaggleのカテゴリを新設しました