Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation

TL;DR

This paper introduces InsTeacher3D, a semi-supervised 3D instance segmentation method that relies solely on instance consistency regularization, avoiding noisy semantic pseudo labels, and demonstrates superior performance on large-scale datasets.

Contribution

The paper proposes a novel semi-supervised framework using instance consistency regularization and a dedicated 3D instance segmentation model, DKNet, to improve segmentation accuracy without semantic pseudo labels.

Findings

Outperforms previous semi-supervised methods on large-scale datasets.

Effectively leverages unlabeled data through instance-only regularization.

Demonstrates robustness against semantic label noise.

Abstract

Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored self-training frameworks, which rely on high-quality pseudo labels for consistency regularization. They intuitively utilize both instance and semantic pseudo labels in a joint learning manner. However, semantic pseudo labels contain numerous noise derived from the imbalanced category distribution and natural confusion of similar but distinct categories, which leads to severe collapses in self-training. Motivated by the observation that 3D instances are non-overlapping and spatially separable, we ask whether we can solely rely on instance consistency regularization for improved semi-supervised segmentation. To this end, we propose a novel self-training network InsTeacher3D to explore and exploit pure instance knowledge from unlabeled data. We first build a parallel base 3D instance segmentation model DKNet, which distinguishes each instance from the others via discriminative instance kernels without reliance on semantic segmentation. Based on DKNet, we further design a novel instance consistency regularization framework to generate and leverage high-quality instance pseudo labels. Experimental results on multiple large-scale datasets show that the InsTeacher3D significantly outperforms prior state-of-the-art semi-supervised approaches. Code is available: https://github.com/W1zheng/InsTeacher3D.