iffDetector: Inference-aware Feature Filtering for Object Detection
This work addresses a bottleneck in object detection by optimizing features during inference, offering a plug-and-play solution with negligible computational overhead.
The paper tackles the problem of feature optimization during inference in CNN-based object detectors by proposing an Inference-aware Feature Filtering (IFF) module, which enhances features and suppresses noise, leading to consistent performance improvements on PASCAL VOC and MS COCO datasets.
Modern CNN-based object detectors focus on feature configuration during training but often ignore feature optimization during inference. In this paper, we propose a new feature optimization approach to enhance features and suppress background noise in both the training and inference stages. We introduce a generic Inference-aware Feature Filtering (IFF) module that can easily be combined with modern detectors, resulting in our iffDetector. Unlike conventional open-loop feature calculation approaches without feedback, the IFF module performs closed-loop optimization by leveraging high-level semantics to enhance the convolutional features. By applying Fourier transform analysis, we demonstrate that the IFF module acts as a negative feedback that theoretically guarantees the stability of feature learning. IFF can be fused with CNN-based object detectors in a plug-and-play manner with negligible computational cost overhead. Experiments on the PASCAL VOC and MS COCO datasets demonstrate that our iffDetector consistently outperforms state-of-the-art methods by significant margins\footnote{The test code and model are anonymously available in https://github.com/anonymous2020new/iffDetector }.