ECLIPSE: Efficient Continual Learning in Panoptic Segmentation with Visual Prompt Tuning

TL;DR

ECLIPSE introduces an efficient continual panoptic segmentation method using visual prompt tuning that reduces training complexity, mitigates forgetting, and maintains plasticity, achieving state-of-the-art results on ADE20K.

Contribution

The paper presents a novel approach that freezes the base model and fine-tunes only prompt embeddings, significantly reducing parameters and improving continual segmentation performance.

Findings

Outperforms existing methods on ADE20K benchmark

Effectively mitigates catastrophic forgetting

Maintains a good balance of plasticity

Abstract

Panoptic segmentation, combining semantic and instance segmentation, stands as a cutting-edge computer vision task. Despite recent progress with deep learning models, the dynamic nature of real-world applications necessitates continual learning, where models adapt to new classes (plasticity) over time without forgetting old ones (catastrophic forgetting). Current continual segmentation methods often rely on distillation strategies like knowledge distillation and pseudo-labeling, which are effective but result in increased training complexity and computational overhead. In this paper, we introduce a novel and efficient method for continual panoptic segmentation based on Visual Prompt Tuning, dubbed ECLIPSE. Our approach involves freezing the base model parameters and fine-tuning only a small set of prompt embeddings, addressing both catastrophic forgetting and plasticity and significantly reducing the trainable parameters. To mitigate inherent challenges such as error propagation and semantic drift in continual segmentation, we propose logit manipulation to effectively leverage common knowledge across the classes. Experiments on ADE20K continual panoptic segmentation benchmark demonstrate the superiority of ECLIPSE, notably its robustness against catastrophic forgetting and its reasonable plasticity, achieving a new state-of-the-art. The code is available at https://github.com/clovaai/ECLIPSE.