Review — VoVNet/OSANet: An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection

OSA Module, Better Module Design Than Dense Block in DenseNet, Outperforms Pelee, DenseNet, ResNet Backbones

Outline

1. One-Shot Aggregation (OSA) Module in VoVNet

Aggregation Methods

Dense connections induce high memory access cost (MAC) which is paid by energy and time.

The dense connection imposes the use of bottleneck structure which harms the efficiency of GPU parallel computation.

Also, dense connection makes later intermediate layer produce the features that are better but also similar to the features from former layers. In this case, the final layer is not required to learn to aggregate both features because they are representing redundant information.

One-shot aggregation (OSA) module is designed to aggregate its feature in the last layer at once, as shown above.

2. VoVNet: Network Architecture

VoVNet: Network Architecture

There are two types of VoVNet: lightweight network, e.g., VoVNet-27-slim, and large-scale network, e.g., VoVNet-39/57.

3. Experimental Results

Comparisons of lightweight models in terms of the computation and energy efficiency
Comparison with lightweight object detectors on VOC 2007 test set

The proposed VoVNet-27-slim based DSOD300 achieves 74.87%, which is better than DenseNet-67 based one even with comparable parameters.

The VoVNet-27-slim based DSOD also outperforms Pelee by a large margin of 3.97% at much faster speed.

Comparisons of large-scale models on RefineDet320
Comparison backbone networks on RefineDet320 on COCO test-dev set

Furthermore, VoVNet improves 1.9%/1.2% small object AP gain from DenseNet121/161, which suggests that generating more features by OSA is better than generating deep features by dense connection on small object detection.

Detection and segmentation results using Mask R-CNN with Group Normalization (Group Norm, GN) trained from scratch for 3× schedule and evaluted on COCO val set.

For object detection task, with faster speed, VoVNet-39 obtains 2.2%/0.9% absolute AP gains compared to ResNet-50/101, respectively.

For instance segmentation task, VoVNet-39 also improves 1.6%/0.4% AP from ResNet-50/101.

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store