CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation

TL;DR

CoinSeg introduces a contrastive learning approach emphasizing intra- and inter-class diversity to improve incremental semantic segmentation, balancing plasticity and stability for better long-term performance.

Contribution

The paper proposes CoinSeg, a novel method that enhances discriminative feature representations using contrastive learning with multiple centroids and pseudo-labels for incremental segmentation.

Findings

Outperforms previous methods on Pascal VOC 2012 and ADE20K datasets.

Achieves superior results in long-term incremental scenarios.

Effectively balances model stability and plasticity.

Abstract

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.