Object detectors involving a NAS-gate convolutional module and capsule attention module

Abstract

Several state-of-the-art object detectors have demonstrated outstanding performances by optimizing feature representation through modification of the backbone architecture and exploitation of a feature pyramid. To determine the effectiveness of this approach, we explore the modification of object detectors’ backbone and feature pyramid by utilizing Neural Architecture Search (NAS) and Capsule Network. We introduce two modules, namely, NAS-gate convolutional module and Capsule Attention module. The NAS-gate convolutional module optimizes standard convolution in a backbone network based on differentiable architecture search cooperation with multiple convolution conditions to overcome object scale variation problems. The Capsule Attention module exploits the strong spatial relationship encoding ability of the capsule network to generate a spatial attention mask, which emphasizes important features and suppresses unnecessary features in the feature pyramid, in order to optimize the feature representation and localization capability of the detectors. Experimental results indicate that the NAS-gate convolutional module can alleviate the object scale variation problem and the Capsule Attention network can help to avoid inaccurate localization. Next, we introduce NASGC-CapANet, which incorporates the two modules, i.e., a NAS-gate convolutional module and capsule attention module. Results of comparisons against state-of-the-art object detectors on the MS COCO val-2017 dataset demonstrate that NASGC-CapANet-based Faster R-CNN significantly outperforms the baseline Faster R-CNN with a ResNet-50 backbone and a ResNet-101 backbone by mAPs of 2.7% and 2.0%, respectively. Furthermore, the NASGC-CapANet-based Cascade R-CNN achieves a box mAP of 43.8% on the MS COCO test-dev dataset.

Neural Architecture Search Survey: A Computer Vision Perspective

“…In addition, the integrated progressive shrinking strategy to facilitate dynamic distillation allows the elastic teacher pool to be trained, and thus teacher detectors can be sampled without additional costs in the subsequent searches. In a 2022 study, Viriyasaranon et al [ 98 ] proposed NASGC-CapANet, designed to explore the backbone of object detectors and the feature pyramid representations using NAS and the capsule network. In the study, the NAS-gate convolutional module and the capsule attention module were introduced.…”