Selective Feature Connection Mechanism: Concatenating Multi-layer CNN Features with a Feature Selector
This work addresses the issue of background clutter and semantic ambiguity in low-layer CNN features for computer vision tasks, offering a general network architecture that is incremental in nature.
The paper tackled the problem of effectively combining multi-layer CNN features by proposing a Selective Feature Connection Mechanism (SFCM) that selectively links low-level to high-level features using a feature selector, resulting in improved performance on tasks like image classification, scene text detection, and image-to-image translation.
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.