R-FCN

In contrast to previous region-based detectors such as Fast/Faster R-CNN [6, 18] that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image.


To achieve this goal, we propose position-sensitive score maps to address a dilemma between translation-invariance in image classification and translation-variance in object detection.


Our method can thus naturally adopt fully convolutional image classifier backbones, such as the latest Residual Networks   (ResNets) [9], for object detection. We show competitive results on the PASCAL VOC datasets (e.g., 83.6% mAP on the 2007 set) with the 101-layer ResNet.


Code is made publicly available at: https://github.com/daijifeng001/r-fcn


A prevalent family [8, 6, 18] of deep networks for object detection can be divided into two subnetworks by the Region-of-Interest (RoI) pooling layer [6]: (i) a shared, “fully convolutional” subnetwork independent of RoIs, and (ii) an RoI-wise subnetwork that does not share computation. This decomposition [8] was historically resulted from the pioneering classification architectures, such as AlexNet [10] and VGG Nets [23], that consist of two subnetworks by design — a convolutional subnetwork ending with a spatial pooling layer, followed by several fully-connected (fc) layers. Thus the (last) spatial pooling layer in image classification networks is naturally turned into the RoI pooling layer in object detection networks [8, 6, 18].


But recent state-of-the-art image classification networks such as Residual Nets (ResNets) [9] and GoogLeNets [24, 26] are by design fully convolutional2 . By analogy, it appears natural to use all convolutional layers to construct the shared, convolutional subnetwork in the object detection architecture, leaving the RoI-wise subnetwork no hidden layer. However, as empirically investigated in this work, this naïve solution turns out to have considerably inferior detection accuracy that does not match the network’s superior classification accuracy. To remedy this issue, in the ResNet paper [9] the RoI pooling layer of the Faster R-CNN detector [18] is unnaturally inserted between two sets of convolutional layers — this creates a deeper RoI-wise subnetwork that improves accuracy, at the cost of lower speed due to the unshared per-RoI computation


We argue that the aforementioned unnatural design is caused by a dilemma of increasing translation invariance for image classification vs. respecting translation variance for object detection. On one hand, the image-level classification task favors translation invariance — shift of an object inside an image should be indiscriminative. Thus, deep (fully) convolutional architectures that are as translationinvariant as possible are preferable as evidenced by the leading results on ImageNet classification


On the other hand, the object detection task needs localization representations that are translation-variant to an extent. For example, translation of an object inside a candidate box should produce meaningful responses for describing how good the candidate box overlaps the object. We hypothesize that deeper convolutional layers in an image classification network are less sensitive to translation. To address this dilemma, the ResNet paper’s detection pipeline [9] inserts the RoI pooling layer into convolutions — this region-specific operation breaks down translation invariance, and the post-RoI convolutional layers are no longer translation-invariant when evaluated across different regions. However, this design sacrifices training and testing efficiency since it introduces a considerable number of region-wise layers (Table 1)