State-of-the-art semantic segmentation approaches increase the receptive field of their models by using either a downsampling path composed of poolings/strided convolutions or successive dilated convolutions. However, it is not clear which operation leads to best results. In this paper, we systematically study the differences introduced by distinct receptive field enlargement methods and their impact on the performance of a novel architecture, called Fully Convolutional DenseResNet (FC-DRN). FC-DRN has a densely connected backbone composed of residual networks. Following standard image segmentation architectures, receptive field enlargement operations that change the representation level are interleaved among residual networks. This allows the model to exploit the benefits of both residual and dense connectivity patterns, namely: gradient flow, iterative refinement of representations, multi-scale feature combination and deep supervision. In order to highlight the potential of our model, we test it on the challenging CamVid urban scene understanding benchmark and make the following observations: 1) downsampling operations outperform dilations when the model is trained from scratch, 2) dilations are useful during the finetuning step of the model, 3) coarser representations require less refinement steps, and 4) ResNets (by model construction) are good regularizers, since they can reduce the model capacity when needed. Finally, we compare our architecture to alternative methods and report state-of-the-art result on the Camvid dataset, with at least twice fewer parameters.
翻译:最先进的语义分解法增加了模型的可接受领域。 FC-DRN拥有一个由剩余网络组成的紧密连接骨干。在标准图像分解结构之后,可接受、可改变代表水平的外地扩大业务在剩余网络中互换。这让模型能够利用剩余和密集连接模式的好处,即:梯度流、反复完善表达方式、多尺度特征组合和深入监督。为了突出模型的潜力,我们用具有挑战性的CamVid城市景象理解基准测试它,并发表以下意见:(1) 模型从抓起训练时,模拟业务比其他网络差得多,2) 模型比对模型比差,在模型比对模型进行细化时,比对模型比值最小,在模型进行微调时,比值最小。 3) 模型比值比值比值比值更小,因为模型比值比值更小。 模型比值比值更低, 模型比值比值更低。