# Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation

arXiv: https://arxiv.org/abs/1809.00903 · HTML: https://mlsanity.com/paper/1809.00903/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2018.

## Built on by (most cited first, 29 of 29)

- [Self-supervised Augmentation Consistency for Adapting Semantic Segmentation](https://mlsanity.com/paper/2105.00097/) (2021)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [DANNet: A One-Stage Domain Adaptation Network for Unsupervised Nighttime Semantic Segmentation](https://mlsanity.com/paper/2104.10834/) (2021)
- [Context-Aware Mixup for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.03557/) (2021)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception](https://mlsanity.com/paper/2109.05441/) (2021)
- [Cross-View Regularization for Domain Adaptive Panoptic Segmentation](https://mlsanity.com/paper/2103.02584/) (2021)
- [Deep Symmetric Adaptation Network for Cross-modality Medical Image Segmentation](https://mlsanity.com/paper/2101.06853/) (2021)
- [Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation](https://mlsanity.com/paper/2103.04705/) (2021)
- [BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation](https://mlsanity.com/paper/2108.03267/) (2021)
- [Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning](https://mlsanity.com/paper/2104.11056/) (2021)
- [Self-Adversarial Disentangling for Specific Domain Adaptation](https://mlsanity.com/paper/2108.03553/) (2021)
- [Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Driving](https://mlsanity.com/paper/2304.11928/) (2023)
- [CL3D: Unsupervised Domain Adaptation for Cross-LiDAR 3D Detection](https://mlsanity.com/paper/2212.00244/) (2022)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [NightLab: A Dual-level Architecture with Hardness Detection for Segmentation at Night](https://mlsanity.com/paper/2204.05538/) (2022)
- [Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/2105.10843/) (2021)
- [Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey](https://mlsanity.com/paper/2112.03241/) (2021)
- [Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Data](https://mlsanity.com/paper/2203.10474/) (2022)
- [CONDA: Continual Unsupervised Domain Adaptation Learning in Visual Perception for Self-Driving Cars](https://mlsanity.com/paper/2212.00621/) (2022)
- [Self-Supervised Learning of Domain Invariant Features for Depth Estimation](https://mlsanity.com/paper/2106.02594/) (2021)
- [AdaStereo: An Efficient Domain-Adaptive Stereo Matching Approach](https://mlsanity.com/paper/2112.04974/) (2021)
- [LoopDA: Constructing Self-loops to Adapt Nighttime Semantic Segmentation](https://mlsanity.com/paper/2211.11870/) (2022)
- [TAVP: Task-Adaptive Visual Prompt for Cross-domain Few-shot Segmentation](https://mlsanity.com/paper/2409.05393/) (2024)
- [TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain Augmentation](https://mlsanity.com/paper/2111.15300/) (2021)
- [Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation](https://mlsanity.com/paper/2210.01578/) (2022)
- [CROVIA: Seeing Drone Scenes from Car Perspective via Cross-View Adaptation](https://mlsanity.com/paper/2304.07199/) (2023)
- [MetaPix: Domain Transfer for Semantic Segmentation by Meta Pixel Weighting](https://mlsanity.com/paper/2110.01777/) (2021)
- [CoMaL: Conditional Maximum Likelihood Approach to Self-supervised Domain Adaptation in Long-tail Semantic Segmentation](https://mlsanity.com/paper/2304.07372/) (2023)
- [Bias Loss for Mobile Neural Networks](https://mlsanity.com/paper/2107.11170/) (2021)

## Abstract (arXiv)

Due to the expensive and time-consuming annotations (e.g., segmentation) for real-world images, recent works in computer vision resort to synthetic data. However, the performance on the real image often drops significantly because of the domain shift between the synthetic data and the real images. In this setting, domain adaptation brings an appealing option. The effective approaches of domain adaptation shape the representations that (1) are discriminative for the main task and (2) have good generalization capability for domain shift. To this end, we propose a novel loss function, i.e., Conservative Loss, which penalizes the extreme good and bad cases while encouraging the moderate examples. More specifically, it enables the network to learn features that are discriminative by gradient descent and are invariant to the change of domains via gradient ascend method. Extensive experiments on synthetic to real segmentation adaptation show our proposed method achieves state of the art results. Ablation studies give more insights into properties of the Conservative Loss. Exploratory experiments and discussion demonstrate that our Conservative Loss has good flexibility rather than restricting an exact form.