Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation

  title={Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation},
  author={Francesco Barbato and Marco Toldo and Umberto Michieli and Pietro Zanuttigh},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  • F. Barbato, Marco Toldo, +1 author P. Zanuttigh
  • Published 6 April 2021
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Deep convolutional neural networks for semantic segmentation achieve outstanding accuracy, however they also have a couple of major drawbacks: first, they do not generalize well to distributions slightly different from the one of the training data; second, they require a huge amount of labeled data for their optimization. In this paper, we introduce feature-level space-shaping regularization strategies to reduce the domain discrepancy in semantic segmentation. In particular, for this purpose we… Expand

Figures and Tables from this paper

Adapting Segmentation Networks to New Domains by Disentangling Latent Representations
This work designs and carefully analyze multiple latent space-shaping regularization strategies that work in conjunction to reduce the domain discrepancy in semantic segmentation and proposes a novel performance metric to capture the relative efficacy of an adaptation strategy compared to supervised training. Expand
Night-Time Scene Parsing With a Large Real Dataset
Extensive experiments show that training on NightCity can significantly improve NTSP performances and that the exposure-aware model outperforms the state-of-the-art methods, yielding top performances on the authors' dataset as well as existing datasets. Expand
Road Scenes Segmentation Across Different Domains by Disentangling Latent Representations
This work design and carefully analyze multiple latent spaceshaping regularization strategies that work together to reduce the domain shift, and proposes a novel evaluation metric to capture the relative performance of an adapted model with respect to supervised training. Expand


The Cityscapes Dataset for Semantic Urban Scene Understanding
This work introduces Cityscapes, a benchmark suite and large-scale dataset to train and test approaches for pixel-level and instance-level semantic labeling, and exceeds previous attempts in terms of dataset size, annotation richness, scene variability, and complexity. Expand
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
This paper generates a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations, and conducts experiments with DCNNs that show how the inclusion of SYnTHIA in the training stage significantly improves performance on the semantic segmentation task. Expand
Domain Adaptation by Class Centroid Matching and Local Manifold Self-Learning
This paper proposes a novel domain adaptation approach, which can thoroughly explore the data distribution structure of target domain and regards the samples within the same cluster in target domain as a whole rather than individuals and assigns pseudo-labels to the target cluster by class centroid matching. Expand
Contrastive Adaptation Network for Unsupervised Domain Adaptation
This paper proposes Contrastive Adaptation Network optimizing a new metric which explicitly models the intra- class domain discrepancy and the inter-class domain discrepancy, and designs an alternating update strategy for training CAN in an end-to-end manner. Expand
Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings
An effective Unsupervised Domain Adaptation (UDA) strategy, based on a feature clustering method that captures the different semantic modes of the feature distribution and groups features of the same class into tight and well-separated clusters is proposed. Expand
Unsupervised Domain Adaptation in Semantic Segmentation: a Review
The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation of deep networks for semantic segmentation, and a comparison of the performance of the various methods in the widely used autonomous driving scenario is presented. Expand
Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations
This paper focuses on class incremental continual learning in semantic segmentation, where new categories are made available over time while previous training data is not retained, and shapes the latent space to reduce forgetting whilst improving the recognition of novel classes. Expand
DACS: Domain Adaptation via Cross-domain Mixed Sampling
DACS: Domain Adaptation via Cross-domain mixed Sampling, which mixes images from the two domains along with the corresponding labels and pseudo-labels, and achieves state-of-the-art results for GTA5 to Cityscapes, a common synthetic-to-real semantic segmentation benchmark for UDA. Expand
HOTA: A Higher Order Metric for Evaluating Multi-object Tracking
This work presents a novel MOT evaluation metric, higher order tracking accuracy (HOTA), which explicitly balances the effect of performing accurate detection, association and localization into a single unified metric for comparing trackers. Expand
Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training
Experimental results prove the effectiveness of the proposed strategy in adapting a segmentation network trained on synthetic datasets like GTA5 and SYNTHIA, to real world datasets like Cityscapes and Mapillary. Expand