ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition

30 Nov 2020 Hsin-Pai Cheng Feng Liang Meng Li Bowen Cheng Feng Yan Hai Li Vikas Chandra Yiran Chen

Scale variance among different sizes of body parts and objects is a challenging problem for visual recognition tasks. Existing works usually design dedicated backbone or apply Neural architecture Search(NAS) for each task to tackle this challenge... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper


 Ranked #1 on Multi-Person Pose Estimation on CrowdPose (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Multi-Person Pose Estimation COCO test-dev HigherHRNet (ScaleNet_P4) AP 71.6 # 4
APL 77.2 # 1
APM 67.5 # 1
AP50 90.3 # 1
AP75 78.2 # 1
AR 76.0 # 1
AR50 92.3 # 1
Multi-Person Pose Estimation CrowdPose HigherHRNet (ScaleNet_P4) mAP @0.5:0.95 71.3 # 1

Methods used in the Paper


METHOD TYPE
Residual Connection
Skip Connections
ReLU
Activation Functions
Softmax
Output Functions
Batch Normalization
Normalization
Average Pooling
Pooling Operations
Scale Aggregation Block
Image Model Blocks
1x1 Convolution
Convolutions
Global Average Pooling
Pooling Operations
Convolution
Convolutions
Bottleneck Residual Block
Skip Connection Blocks
Dense Connections
Feedforward Networks
Max Pooling
Pooling Operations
ScaleNet
Convolutional Neural Networks