HAL3D: Hierarchical Active Learning for Fine-Grained 3D Part Labeling
This addresses the high annotation burden in 3D computer vision for researchers and practitioners, though it is incremental as it builds on existing active learning and deep learning methods.
The paper tackles the problem of fine-grained 3D part labeling, which is challenging due to structural variations and requires extensive annotation effort, by developing HAL3D, a hierarchical active learning tool that achieves 100% accuracy with 80% time-saving over manual labeling.
We present the first active learning tool for fine-grained 3D part labeling, a problem which challenges even the most advanced deep learning (DL) methods due to the significant structural variations among the small and intricate parts. For the same reason, the necessary data annotation effort is tremendous, motivating approaches to minimize human involvement. Our labeling tool iteratively verifies or modifies part labels predicted by a deep neural network, with human feedback continually improving the network prediction. To effectively reduce human efforts, we develop two novel features in our tool, hierarchical and symmetry-aware active labeling. Our human-in-the-loop approach, coined HAL3D, achieves 100% accuracy (barring human errors) on any test set with pre-defined hierarchical part labels, with 80% time-saving over manual effort.