Focal Modulation Networks

22 Mar 2022  ·  Jianwei Yang, Chunyuan Li, Xiyang Dai, Lu Yuan, Jianfeng Gao ·

We propose focal modulation networks (FocalNets in short), where self-attention (SA) is completely replaced by a focal modulation mechanism for modeling token interactions in vision. Focal modulation comprises three components: (i) hierarchical contextualization, implemented using a stack of depth-wise convolutional layers, to encode visual contexts from short to long ranges, (ii) gated aggregation to selectively gather contexts for each query token based on its content, and (iii) element-wise modulation or affine transformation to inject the aggregated context into the query. Extensive experiments show FocalNets outperform the state-of-the-art SA counterparts (e.g., Swin and Focal Transformers) with similar computational costs on the tasks of image classification, object detection, and segmentation. Specifically, FocalNets with tiny and base size achieve 82.3% and 83.9% top-1 accuracy on ImageNet-1K. After pretrained on ImageNet-22K in 224 resolution, it attains 86.5% and 87.3% top-1 accuracy when finetuned with resolution 224 and 384, respectively. When transferred to downstream tasks, FocalNets exhibit clear superiority. For object detection with Mask R-CNN, FocalNet base trained with 1\times outperforms the Swin counterpart by 2.1 points and already surpasses Swin trained with 3\times schedule (49.0 v.s. 48.5). For semantic segmentation with UPerNet, FocalNet base at single-scale outperforms Swin by 2.4, and beats Swin at multi-scale (50.5 v.s. 49.7). Using large FocalNet and Mask2former, we achieve 58.5 mIoU for ADE20K semantic segmentation, and 57.9 PQ for COCO Panoptic Segmentation. Using huge FocalNet and DINO, we achieved 64.3 and 64.4 mAP on COCO minival and test-dev, respectively, establishing new SoTA on top of much larger attention-based models like Swinv2-G and BEIT-3. Code and checkpoints are available at https://github.com/microsoft/FocalNet.

PDF Abstract

Results from the Paper


Ranked #8 on Object Detection on COCO minival (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Semantic Segmentation ADE20K FocalNet-L (Mask2Former) Validation mIoU 58.5 # 13
Object Detection COCO minival FocalNet-H (DINO) box AP 64.2 # 8
Panoptic Segmentation COCO minival FocalNet-L (Mask2Former (200 queries)) PQ 57.9 # 11
AP 48.4 # 9
Object Detection COCO minival FocalNet-T (LRF, Cascade Mask R-CNN) box AP 51.5 # 70
AP50 70.3 # 20
AP75 56.0 # 12
Object Detection COCO minival FocalNet-T (SRF, Cascade Mask R-CNN) AP50 70.1 # 21
AP75 55.8 # 14
Object Detection COCO test-dev FocalNet-H (DINO) box mAP 64.4 # 9

Methods