Brief Review — GhostNets on Heterogeneous Devices via Cheap Operations
CPU & GPU Efficient C-GhostNet & G-GhostNet
GhostNets on Heterogeneous Devices via Cheap Operations,
C-GhostNet & G-GhostNet, by University of Chinese Academy of Sciences, Huawei Noah’s Ark Lab, The University of Sydney, and University of Macau,
2022 IJCV, Over 10 Citations (Sik-Ho Tsang @ Medium)Image Classification
1989 … 2023 [Vision Permutator (ViP)] [ConvMixer]
==== My Other Paper Readings Are Also Over Here ====
- By stacking the proposed CPU-efficient Ghost (C-Ghost) module, C-GhostNet is designed. Simiilarly, by stacking the proposed GPU-efficient Ghost (G-Ghost) module, G-GhostNet is designed.
Outline
- C-GhostNet
- G-GhostNet
- Results
1. C-GhostNet
- (This part is the same as GhostNet. Please feel free to read GhostNet, or skip it if you know GhostNet well.)
1.1. Findings
- It is observed that there are many similar feature maps. There is redundancy in feature maps.
1.2. C-Ghost Module
In brief for C-GhostNet module, some input feature maps are kept unchanged as output by identity connection. Some are passed through cheap operations to generate some new feature maps.
- In practice, there could be several different cheap operations in a C-Ghost module, e.g., 3×3 and 5×5 linear kernels. Finally, 1×1 is chosen as cheap operation.
1.3. C-Ghost Bottleneck
The proposed ghost bottleneck mainly consists of two stacked C-Ghost modules. The first C-Ghost module acts as an expansion layer increasing the number of channels. The second C-Ghost module reduces the number of channels to match the shortcut path. ReLU and BN is used.
1.4. C-GhostNet
C-GhostNet is formed by stacking ghost bottleneck.
2. G-GhostNet
2.1. Findings
In this paper, it is even found that the feature maps at different layers/blocks are also similar.
2.2. G-Ghost Stage
- (a) Vanilla CNN stages.
- (b) C-Ghost module concept applied across multiple blocks.
(c) Mix operation added on top of (b).
- A global average pooling is applied to obtain the aggregated feature z.
- A fully connected layer is then applied to transform z into the same domain as Y.
G-GhostNet is formed by using the G-Ghost module.
3. Results
3.1. C-GhostNet on ImageNet
C-GhostNet outperforms other competitors consistently at various computational complexity levels, since C-GhostNet is more efficient in utilizing computation resources for generating feature maps.
3.2. C-GhostNet on MS COCO
On MS COCO, with significantly lower computational costs, C-GhostNet achieves similar mAP with MobileNetV2 and MobileNetV3.
3.3. G-GhostNet on ImageNet
G-Ghost-RegNet achieves the optimal accuracy-FLOPs trade-off and accuracy-latency trade-off.
3.4. G-GhostNet on MS COCO
G-Ghost-RegNetX-3.2GF suppresses ResNet50 and RegNetX-3.2GF-0.75 by a significant margin, and meanwhile achieves a faster inference speed.