DSIC: Dynamic Sample-Individualized Connector for Multi-Scale Object Detection

TL;DR

The paper introduces DSIC, a dynamic feature fusion module for multi-scale object detection that adapts to different samples, improving detection accuracy over fixed-architecture methods.

Contribution

It proposes a novel Dynamic Sample-Individualized Connector (DSIC) with ISG and CSG components, enabling adaptive feature fusion for better multi-scale object detection.

Findings

Outperforms state-of-the-art methods on benchmark datasets.

Demonstrates effective sample-specific feature fusion.

Plug-and-play design allows easy integration into existing backbones.

Abstract

Although object detection has reached a milestone thanks to the great success of deep learning, the scale variation is still the key challenge. Integrating multi-level features is presented to alleviate the problems, like the classic Feature Pyramid Network (FPN) and its improvements. However, the specifically designed feature integration modules of these methods may not have the optimal architecture for feature fusion. Moreover, these models have fixed architectures and data flow paths, when fed with various samples. They cannot adjust and be compatible with each kind of data. To overcome the above limitations, we propose a Dynamic Sample-Individualized Connector (DSIC) for multi-scale object detection. It dynamically adjusts network connections to fit different samples. In particular, DSIC consists of two components: Intra-scale Selection Gate (ISG) and Cross-scale Selection Gate (CSG). ISG adaptively extracts multi-level features from backbone as the input of feature integration. CSG automatically activate informative data flow paths based on the multi-level features. Furthermore, these two components are both plug-and-play and can be embedded in any backbone. Experimental results demonstrate that the proposed method outperforms the state-of-the-arts.