Instance Scale Normalization for image understanding
This addresses scale variation challenges in computer vision tasks like object detection, instance segmentation, and human pose estimation, representing a novel paradigm rather than an incremental improvement.
The paper tackles the problem of scale variation in object detection by proposing Instance Scale Normalization (ISN), which compresses object scales into a consistent range, resulting in a single model achieving 46.5 mAP on COCO test-dev with a ResNet-101 backbone.
Scale variation remains a challenging problem for object detection. Common paradigms usually adopt multiscale training & testing (image pyramid) or FPN (feature pyramid network) to process objects in a wide scale range. However, multi-scale methods aggravate more variations of scale that even deep convolution neural networks with FPN cannot handle well. In this work, we propose an innovative paradigm called Instance Scale Normalization (ISN) to resolve the above problem. ISN compresses the scale space of objects into a consistent range (ISN range), in both training and testing phases. This reassures the problem of scale variation fundamentally and reduces the difficulty of network optimization. Experiments show that ISN surpasses multi-scale counterpart significantly for object detection, instance segmentation, and multi-task human pose estimation, on several architectures. On COCO test-dev, our single model based on ISN achieves 46.5 mAP with a ResNet-101 backbone, which is among the state-of-the-art (SOTA) candidates for object detection.