Conditional Convolutions for Instance Segmentation

TL;DR

CondInst introduces a fully convolutional, instance-aware approach for instance segmentation using dynamic conditional convolutions, achieving higher accuracy and faster inference than traditional ROI-based methods like Mask R-CNN.

Contribution

The paper presents a novel framework that replaces ROI operations with dynamic, instance-conditioned convolutions, simplifying the architecture and improving performance.

Findings

Outperforms recent methods on COCO dataset

Eliminates the need for ROI cropping and feature alignment

Achieves faster inference with a compact mask head

Abstract

We propose a simple yet effective instance segmentation framework, termed CondInst (conditional convolutions for instance segmentation). Top-performing instance segmentation methods such as Mask R-CNN rely on ROI operations (typically ROIPool or ROIAlign) to obtain the final instance masks. In contrast, we propose to solve instance segmentation from a new perspective. Instead of using instance-wise ROIs as inputs to a network of fixed weights, we employ dynamic instance-aware networks, conditioned on instances. CondInst enjoys two advantages: 1) Instance segmentation is solved by a fully convolutional network, eliminating the need for ROI cropping and feature alignment. 2) Due to the much improved capacity of dynamically-generated conditional convolutions, the mask head can be very compact (e.g., 3 conv. layers, each having only 8 channels), leading to significantly faster inference. We demonstrate a simpler instance segmentation method that can achieve improved performance in both accuracy and inference speed. On the COCO dataset, we outperform a few recent methods including well-tuned Mask RCNN baselines, without longer training schedules needed. Code is available: https://github.com/aim-uofa/adet