TensorMask: A Foundation for Dense Object Segmentation

Sliding-window object detectors that generate bounding-box object predictions over a dense, regular grid have advanced rapidly and proven popular. In contrast, modern instance segmentation approaches are dominated by methods that first detect object bounding boxes, and then crop and segment these regions, as popularized by Mask R-CNN... (read more)

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Instance Segmentation COCO test-dev TensorMask (ResNet-101-FPN) mask AP 37.3% # 32

Methods used in the Paper


METHOD TYPE
Softmax
Output Functions
RoIAlign
RoI Feature Extractors
Average Pooling
Pooling Operations
Mask R-CNN
Instance Segmentation Models
Residual Connection
Skip Connections
ReLU
Activation Functions
1x1 Convolution
Convolutions
Batch Normalization
Normalization
Bottleneck Residual Block
Skip Connection Blocks
Global Average Pooling
Pooling Operations
Residual Block
Skip Connection Blocks
Kaiming Initialization
Initialization
Max Pooling
Pooling Operations
Convolution
Convolutions
ResNet
Convolutional Neural Networks