FaPN: Feature-aligned Pyramid Network for Dense Image Prediction

ICCV 2021  ·  Shihua Huang, Zhichao Lu, Ran Cheng, Cheng He ·

Recent advancements in deep neural networks have made remarkable leap-forwards in dense image prediction. However, the issue of feature alignment remains as neglected by most existing approaches for simplicity. Direct pixel addition between upsampled and local features leads to feature maps with misaligned contexts that, in turn, translate to mis-classifications in prediction, especially on object boundaries. In this paper, we propose a feature alignment module that learns transformation offsets of pixels to contextually align upsampled higher-level features; and another feature selection module to emphasize the lower-level features with rich spatial details. We then integrate these two modules in a top-down pyramidal architecture and present the Feature-aligned Pyramid Network (FaPN). Extensive experimental evaluations on four dense prediction tasks and four datasets have demonstrated the efficacy of FaPN, yielding an overall improvement of 1.2 - 2.6 points in AP / mIoU over FPN when paired with Faster / Mask R-CNN. In particular, our FaPN achieves the state-of-the-art of 56.7% mIoU on ADE20K when integrated within Mask-Former. The code is available from https://github.com/EMI-Group/FaPN.

PDF Abstract ICCV 2021 PDF ICCV 2021 Abstract


Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation ADE20K FaPN (MaskFormer, Swin-L, ImageNet-22k pretrain) Validation mIoU 56.7 # 32
Semantic Segmentation ADE20K val FaPN (MaskFormer, Swin-L, ImageNet-22k pretrain) mIoU 56.7 # 22