# Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector

Source: [Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector](<https://www.sota2.com/research/paper/68fa75d61e209131cea6a268>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:42:38.626Z

Authors: Chen Du, Chunheng Wang, Yanna Wang, Cunzhao Shi, Baihua Xiao

Published: 2018-11-15T10:58:21.000Z

## Abstract

Different layers of deep convolutional neural networks(CNNs) can encode different-level information. High-layer features always contain more semantic information, and low-layer features contain more detail information. However, low-layer features suffer from the background clutter and semantic ambiguity. During visual recognition, the feature combination of the low-layer and high-level features plays an important role in context modulation. If directly combining the high-layer and low-layer features, the background clutter and semantic ambiguity may be caused due to the introduction of detailed information. In this paper, we propose a general network architecture to concatenate CNN features of different layers in a simple and effective way, called Selective Feature Connection Mechanism (SFCM). Low-level features are selectively linked to high-level features with a feature selector which is generated by high-level features. The proposed connection mechanism can effectively overcome the above-mentioned drawbacks. We demonstrate the effectiveness, superiority, and universal applicability of this method on multiple challenging computer vision tasks, including image classification, scene text detection, and image-to-image translation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1811.06295>)

[PDF](<https://arxiv.org/pdf/1811.06295.pdf>)
