Recursively Refined R-CNN: Instance Segmentation with Self-RoI Rebalancing

by   Leonardo Rossi, et al.

Within the field of instance segmentation, most of the state-of-the-art deep learning networks rely nowadays on cascade architectures, where multiple object detectors are trained sequentially, re-sampling the ground truth at each step. This offers a solution to the problem of exponentially vanishing positive samples. However, it also translates into an increase in network complexity in terms of the number of parameters. To address this issue, we propose Recursively Refined R-CNN (R^3-CNN) which avoids duplicates by introducing a loop mechanism instead. At the same time, it achieves a quality boost using a recursive re-sampling technique, where a specific IoU quality is utilized in each recursion to eventually equally cover the positive spectrum. Our experiments highlight the specific encoding of the loop mechanism in the weights, requiring its usage at inference time. The R^3-CNN architecture is able to surpass the recently proposed HTC model, while reducing the number of parameters significantly. Experiments on COCO minival 2017 dataset show performance boost independently from the utilized baseline model. The code is available online at


page 1

page 2

page 3

page 4


Cascade R-CNN: High Quality Object Detection and Instance Segmentation

In object detection, the intersection over union (IoU) threshold is freq...

Cascade R-CNN: Delving into High Quality Object Detection

In object detection, an intersection over union (IoU) threshold is requi...

InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting

Instance segmentation requires a large number of training samples to ach...

A novel Region of Interest Extraction Layer for Instance Segmentation

Given the wide diffusion of deep neural network architectures for comput...

SCNet: Training Inference Sample Consistency for Instance Segmentation

Cascaded architectures have brought significant performance improvement ...

Please sign up or login with your details

Forgot password? Click here to reset