# A Cross-Season Correspondence Dataset for Robust Semantic Segmentation

arXiv: https://arxiv.org/abs/1903.06916 · HTML: https://mlsanity.com/paper/1903.06916/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Mar 2019.

## Built on by (most cited first, 28 of 28)

- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Learning Accurate Dense Correspondences and When to Trust Them](https://mlsanity.com/paper/2101.01710/) (2021)
- [PDC-Net+: Enhanced Probabilistic Dense Correspondence Network](https://mlsanity.com/paper/2109.13912/) (2021)
- [A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction](https://mlsanity.com/paper/2207.01223/) (2022)
- [Warp Consistency for Unsupervised Learning of Dense Correspondences](https://mlsanity.com/paper/2104.03308/) (2021)
- [Multi-scale Matching Networks for Semantic Correspondence](https://mlsanity.com/paper/2108.00211/) (2021)
- [Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions](https://mlsanity.com/paper/2207.06825/) (2022)
- [Missing Modality Robustness in Semi-Supervised Multi-Modal Semantic Segmentation](https://mlsanity.com/paper/2304.10756/) (2023)
- [Improving Visual Place Recognition Performance by Maximising Complementarity](https://mlsanity.com/paper/2102.08416/) (2021)
- [An Efficient and Scalable Collection of Fly-inspired Voting Units for Visual Place Recognition in Changing Environments](https://mlsanity.com/paper/2109.10986/) (2021)
- [Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation](https://mlsanity.com/paper/2303.05194/) (2023)
- [CGiS-Net: Aggregating Colour, Geometry and Implicit Semantic Features for Indoor Place Recognition](https://mlsanity.com/paper/2202.02070/) (2022)
- [Highly-Efficient Binary Neural Networks for Visual Place Recognition](https://mlsanity.com/paper/2202.12375/) (2022)
- [SwitchHit: A Probabilistic, Complementarity-Based Switching System for Improved Visual Place Recognition in Changing Environments](https://mlsanity.com/paper/2203.00591/) (2022)
- [FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditions](https://mlsanity.com/paper/2407.13437/) (2024)
- [LIFE: Lighting Invariant Flow Estimation](https://mlsanity.com/paper/2104.03097/) (2021)
- [Unsupervised Complementary-aware Multi-process Fusion for Visual Place Recognition](https://mlsanity.com/paper/2112.04701/) (2021)
- [Template NeRF: Towards Modeling Dense Shape Correspondences from Category-Specific Object Images](https://mlsanity.com/paper/2111.04237/) (2021)
- [ROVER: A Multi-Season Dataset for Visual SLAM](https://mlsanity.com/paper/2412.02506/) (2024)
- [AEGIS-Net: Attention-guided Multi-Level Feature Aggregation for Indoor Place Recognition](https://mlsanity.com/paper/2312.09538/) (2023)
- [A Novel Image Descriptor with Aggregated Semantic Skeleton Representation for Long-term Visual Place Recognition](https://mlsanity.com/paper/2202.03677/) (2022)
- [Merging Classification Predictions with Sequential Information for Lightweight Visual Place Recognition in Changing Environments](https://mlsanity.com/paper/2210.00834/) (2022)
- [A Complementarity-Based Switch-Fuse System for Improved Visual Place Recognition](https://mlsanity.com/paper/2303.00714/) (2023)
- [Semantic Validation in Structure from Motion](https://mlsanity.com/paper/2304.02420/) (2023)
- [An Evaluation and Ranking of Different Voting Schemes for Improved Visual Place Recognition](https://mlsanity.com/paper/2305.05705/) (2023)
- [Employing Universal Voting Schemes for Improved Visual Place Recognition Performance](https://mlsanity.com/paper/2405.02297/) (2024)
- [Learning Street View Representations with Spatiotemporal Contrast](https://mlsanity.com/paper/2502.04638/) (2025)
- [Calibrating Retrieval Geometry: Reliability-Guided Training-Free Aggregation for Visual Place Recognition](https://mlsanity.com/paper/2609.25937/) (2026)

## Abstract (arXiv)

In this paper, we present a method to utilize 2D-2D point matches between images taken during different image conditions to train a convolutional neural network for semantic segmentation. Enforcing label consistency across the matches makes the final segmentation algorithm robust to seasonal changes. We describe how these 2D-2D matches can be generated with little human interaction by geometrically matching points from 3D models built from images. Two cross-season correspondence datasets are created providing 2D-2D matches across seasonal changes as well as from day to night. The datasets are made publicly available to facilitate further research. We show that adding the correspondences as extra supervision during training improves the segmentation performance of the convolutional neural network, making it more robust to seasonal changes and weather conditions.