Class incremental semantic segmentation aims to strike a balance between the model's stability and plasticity by maintaining old knowledge while adapting to new concepts. However, most state-of-the-art methods use the freeze strategy for stability, which compromises the model's plasticity.In contrast, releasing parameter training for plasticity could lead to the best performance for all categories, but this requires discriminative feature representation.Therefore, we prioritize the model's plasticity and propose the Contrast inter- and intra-class representations for Incremental Segmentation (CoinSeg), which pursues discriminative representations for flexible parameter tuning. Inspired by the Gaussian mixture model that samples from a mixture of Gaussian distributions, CoinSeg emphasizes intra-class diversity with multiple contrastive representation centroids. Specifically, we use mask proposals to identify regions with strong objectness that are likely to be diverse instances/centroids of a category. These mask proposals are then used for contrastive representations to reinforce intra-class diversity. Meanwhile, to avoid bias from intra-class diversity, we also apply category-level pseudo-labels to enhance category-level consistency and inter-category diversity. Additionally, CoinSeg ensures the model's stability and alleviates forgetting through a specific flexible tuning strategy. We validate CoinSeg on Pascal VOC 2012 and ADE20K datasets with multiple incremental scenarios and achieve superior results compared to previous state-of-the-art methods, especially in more challenging and realistic long-term scenarios. Code is available at https://github.com/zkzhang98/CoinSeg.

翻译：类增量语义分割旨在平衡模型的稳定性与可塑性，即在保持旧知识的同时适应新概念。然而，现有大多数先进方法采用冻结策略以维持稳定性，但这会牺牲模型的可塑性。相反，释放参数训练以提升可塑性，虽能促使模型在所有类别上达到最优性能，但需依赖判别性特征表示。为此，我们优先考虑模型的可塑性，提出面向增量分割的类内外表示对比方法（CoinSeg），通过追求判别性表示实现灵活的参数调优。受高斯混合模型从混合高斯分布中采样的启发，CoinSeg 利用多个对比表示中心点强调类内多样性。具体而言，我们采用掩膜提议来识别具有强目标性且可能属于某类别多样化实例/中心点的区域，进而利用这些掩膜提议进行对比表示以强化类内多样性。同时，为避免类内多样性引起的偏差，我们进一步应用类别级伪标签增强类别间一致性及类别间多样性。此外，CoinSeg 通过特定灵活调优策略确保模型稳定性并缓解遗忘问题。我们在Pascal VOC 2012和ADE20K数据集上针对多种增量场景验证了CoinSeg，相较于先前先进方法取得了更优结果，尤其在更具挑战性与现实性的长期场景中表现突出。代码已开源：https://github.com/zkzhang98/CoinSeg。