iffDetector: Inference-aware Feature Filtering for Object Detection
arXiv:2006.12708
Abstract
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 }.
14 pages, 6 figures
References in corpus (9)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- YOLOv3: An Incremental Improvement
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- DSSD : Deconvolutional Single Shot Detector
- FCOS: Fully Convolutional One-Stage Object Detection
- Beyond Skip Connections: Top-Down Modulation for Object Detection
- FreeAnchor: Learning to Match Anchors for Visual Object Detection
- MetaAnchor: Learning to Detect Objects with Customized Anchors
- Bounding Box Regression with Uncertainty for Accurate Object Detection