ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation
This addresses annotation-efficient training for novel classes in instance segmentation, though it appears incremental as it builds on existing weakly-supervised and few-shot approaches.
The paper tackles weakly-supervised low-shot instance segmentation by proposing ENInst, which enhances pixel localization and classification accuracy, resulting in 7.5 times more efficiency in achieving comparable performance to fully-supervised few-shot models.
We address a weakly-supervised low-shot instance segmentation, an annotation-efficient training method to deal with novel classes effectively. Since it is an under-explored problem, we first investigate the difficulty of the problem and identify the performance bottleneck by conducting systematic analyses of model components and individual sub-tasks with a simple baseline model. Based on the analyses, we propose ENInst with sub-task enhancement methods: instance-wise mask refinement for enhancing pixel localization quality and novel classifier composition for improving classification accuracy. Our proposed method lifts the overall performance by enhancing the performance of each sub-task. We demonstrate that our ENInst is 7.5 times more efficient in achieving comparable performance to the existing fully-supervised few-shot models and even outperforms them at times.