Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection
This work addresses a key bottleneck in object detection for computer vision applications, offering an incremental improvement over existing anchor-based methods.
The paper tackled the problem of anchor matching in object detection by proposing a mutual guidance strategy that uses predictions from localization and classification tasks to dynamically assign sample anchors, improving model performance on both tasks. Experiments on PASCAL VOC and MS COCO datasets demonstrated the method's effectiveness and generality.
Most deep learning object detectors are based on the anchor mechanism and resort to the Intersection over Union (IoU) between predefined anchor boxes and ground truth boxes to evaluate the matching quality between anchors and objects. In this paper, we question this use of IoU and propose a new anchor matching criterion guided, during the training phase, by the optimization of both the localization and the classification tasks: the predictions related to one task are used to dynamically assign sample anchors and improve the model on the other task, and vice versa. Despite the simplicity of the proposed method, our experiments with different state-of-the-art deep learning architectures on PASCAL VOC and MS COCO datasets demonstrate the effectiveness and generality of our Mutual Guidance strategy.