Conditional Convolutions for Instance Segmentation

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

Accepted to Proc. European Conf. Computer Vision (ECCV) 2020 as oral presentation

References in corpus (8)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
• Associative Embedding: End-to-End Learning for Joint Detection and Grouping
• CondConv: Conditionally Parameterized Convolutions for Efficient Inference
• Semantic Instance Segmentation via Deep Metric Learning
• EmbedMask: Embedding Coupling for One-stage Instance Segmentation
• DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data

Cited by in corpus (10)

• Sparse R-CNN: End-to-End Object Detection with Learnable Proposals
• Video Instance Segmentation using Inter-Frame Communication Transformers
• Boundary-preserving Mask R-CNN
• Fully Convolutional Networks for Panoptic Segmentation
• DCT-Mask: Discrete Cosine Transform Mask Representation for Instance Segmentation
• Spatial Feature Calibration and Temporal Fusion for Effective One-stage Video Instance Segmentation
• Dynamic Neural Representational Decoders for High-Resolution Semantic Segmentation
• DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
• Instance and Panoptic Segmentation Using Conditional Convolutions
• Towards Fine-grained Large Object Segmentation 1st Place Solution to 3D AI Challenge 2020 -- Instance Segmentation Track