paper-with-me

홈 › Papers

C3AE: Exploring the Limits of Compact Model for Age Estimation

2019-04-10 · CVPR 2019 6 · Chao Zhang, Shuaicheng Liu, Xun Xu, Ce Zhu

Age estimation is a classic learning problem in computer vision. Many larger and deeper CNNs have been proposed with promising performance, such as AlexNet, VggNet, GoogLeNet and ResNet. However, these models are not practical for the embedded/mobile devices. Recently, MobileNets and ShuffleNets have been proposed to reduce the number of parameters, yielding lightweight models. However, their representation has been weakened because of the adoption of depth-wise separable convolution. In this work, we investigate the limits of compact model for small-scale image and propose an extremely Compact yet efficient Cascade Context-based Age Estimation model(C3AE). This model possesses only 1/9 and 1/2000 parameters compared with MobileNets/ShuffleNets and VggNet, while achieves competitive performance. In particular, we re-define age estimation problem by two-points representation, which is implemented by a cascade model. Moreover, to fully utilize the facial context information, multi-branch CNN network is proposed to aggregate multi-scale context. Experiments are carried out on three age estimation datasets. The state-of-the-art performance on compact model has been achieved with a relatively large margin.

📄 PDF Abstract BibTeX arXiv:1904.05059

Code (1)

StevenBanama/C3AE tf

Tasks

Age Estimation

Methods 이 논문이 사용한 방법론

Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Bottleneck Residual Block A Bottleneck Residual Block is a variant of the residual block that utilises 1x1 convolutions to create a bottleneck. The…
Kaiming Initialization 설명 없음
Residual Connection 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…

Similar Papers 제목 키워드 기반

Disentangled Latent Transformer for Interpretable Monocular Height Estimation

2022-01-17 · Zhitong Xiong, Sining Chen, Yilei Shi, Xiao Xiang Zhu

Monocular height estimation (MHE) from remote sensing imagery has high potential in generating 3D city models efficiently for a quick response to natural disasters. Most existing works pursue higher performance. However,…

Semantic SegmentationUnsupervised Semantic Segmentation

EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

2026-03-19 · Longfei Liu, Yongjie Hou, Yang Li, Qirui Wang 외 arxiv

Deploying high-performance dense prediction models on resource-constrained edge devices remains challenging due to strict limits on computation and memory. In practice, lightweight systems for object detection, instance …

Representation LearningInstance SegmentationObject DetectionPose Estimation

Neuromorphic Spiking Ring Attractor for Proprioceptive Joint-State Estimation

2026-04-15 · Federica Ferrari, Flavia Davidhi, Bernard Maacaron, Alberto Motta 외 arxiv

Maintaining stable internal representations of continuous variables is fundamental for effective robotic control. Continuous attractor networks provide a biologically inspired mechanism for encoding such variables, yet n…

Fundamental Limits and Optimization of Multiband Sensing

2022-07-21 · Yubo Wan, An Liu, Rui Du, Tony Xiao Han

Multiband sensing is a promising technology that utilizes multiple non-contiguous frequency bands to achieve high-resolution target sensing. In this paper, we investigate the fundamental limits and optimization of multib…

Vacant Holes for Unsupervised Detection of the Outliers in Compact Latent Representation

2023-06-16 · Misha Glazunov, Apostolis Zarras

Detection of the outliers is pivotal for any machine learning model deployed and operated in real-world. It is essential for the Deep Neural Networks that were shown to be overconfident with such inputs. Moreover, even d…