CC-NET: Image Complexity Guided Network Compression for Biomedical Image Segmentation

Mishra, Suraj; Liang, Peixian; Czajka, Adam; Chen, Danny Z.; Hu, Xiaobo Sharon

doi:10.1109/isbi.2019.8759448

Cited by 26 publications

(13 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All of them, however, require more computing power and memory than a device like Raspberry Pi could offer. Therefore, we adapted the lightweight CC-Net architecture [27] to iris segmentation. CC-Net has a U-Net structure [34], but it leverages information about the image complexity of the training data to compress the network while preserving most of the segmentation accuracy.…”

Section: Iris Segmentationmentioning

confidence: 99%

“…Our open-source software pipeline consists of three modules: segmentation, presentation attack detection, and recognition. We use an image-complexity guided network compression scheme, CC-Net [27], to design a lightweight iris segmentation network that operates with high speed on Raspberry Pi, while producing high-quality masks. The presentation attack detection module is based on the bestperforming methods among all available open-source iris PAD algorithms evaluated to date [12].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Open Source Iris Recognition Hardware and Software with Presentation Attack Detection

Fang

Czajka

2020

2020 IEEE International Joint Conference on Biometrics (IJCB)

Self Cite

View full text Add to dashboard Cite

This paper proposes the first known to us open source hardware and software iris recognition system with presentation attack detection (PAD), which can be easily assembled for about 75 USD using Raspberry Pi board and a few peripherals. The primary goal of this work is to offer a low-cost baseline for spoof-resistant iris recognition, which may (a) stimulate research in iris PAD and allow for easy prototyping of secure iris recognition systems, (b) offer a low-cost secure iris recognition alternative to more sophisticated systems, and (c) serve as an educational platform. We propose a lightweight image complexity-guided convolutional network for fast and accurate iris segmentation, domain-specific human-inspired Binarized Statistical Image Features (BSIF) to build an iris template, and to combine 2D (iris texture) and 3D (photometric stereobased) features for PAD. The proposed iris recognition runs in about 3.2 seconds and the proposed PAD runs in about 4.5 seconds on Raspberry Pi 3B+. The hardware specifications and all source codes of the entire pipeline are made available along with this paper.

show abstract

Section: Iris Segmentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Open Source Iris Recognition Hardware and Software with Presentation Attack Detection

Fang

Czajka

2020

2020 IEEE International Joint Conference on Biometrics (IJCB)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The classification model was trained and validated on the HAM10000 which is composed of 10030 skin images with corresponding class labels. The dataset is composed of 7 important diagnostic categories of skin lesions which are [77] 82.0 Multi-task Framework [47] 88.0 CC-Net [78] 86.8 EXFUSE [79] 88.0 FIGURE 6. The figure compares the general performance of the encoder-decoder network using Dice-coefficient, accuracy, senitivity and specificity when used with CRF and when used without CRF for segmentation of skin lesion images .…”

Section: ) Classification Resultsmentioning

confidence: 99%

FCN-Based DenseNet Framework for Automated Detection and Classification of Skin Lesions in Dermoscopy Images

2020

View full text Add to dashboard Cite

Skin Lesion detection and classification are very critical in diagnosing skin malignancy. Existing Deep learning-based Computer-aided diagnosis (CAD) methods still perform poorly on challenging skin lesions with complex features such as fuzzy boundaries, artifacts presence, low contrast with the background and, limited training datasets. They also rely heavily on a suitable turning of millions of parameters which often leads to over-fitting, poor generalization, and heavy consumption of computing resources. This study proposes a new framework that performs both segmentation and classification of skin lesions for automated detection of skin cancer. The proposed framework consists of two stages: the first stage leverages on an encoder-decoder Fully Convolutional Network (FCN) to learn the complex and inhomogeneous skin lesion features with the encoder stage learning the coarse appearance and the decoder learning the lesion borders details. Our FCN is designed with the sub-networks connected through a series of skip pathways that incorporate long skip and shortcut connections unlike, the only long skip connections commonly used in the traditional FCN, for residual learning strategy and effective training. The network also integrates the Conditional Random Field (CRF) module which employs a linear combination of Gaussian kernels for its pairwise edge potentials for contour refinement and lesion boundaries localization. The second stage proposes a novel FCN-based DenseNet framework that is composed of dense blocks that are merged and connected via the concatenation strategy and transition layer. The system also employs hyperparameters optimization techniques to reduce network complexity and improve computing efficiency. This approach encourages feature reuse and thus requires a small number of parameters and effective with limited data. The proposed model was evaluated on publicly available HAM10000 dataset of over 10000 images consisting of 7 different categories of diseases with 98% accuracy, 98.5% recall, and 99% of AUC score respectively.

show abstract

“…Spatial complexity indicator. Spatial complexity has been commonly used as the basis for estimating image complexity [11,24,33], such as the one proposed in [40]:…”

Section: Dance: Automated Data Slimmingmentioning

confidence: 99%

DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference

Li¹,

Chen²,

Gu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Semantic segmentation for scene understanding is nowadays widely demanded, raising significant challenges for the algorithm efficiency, especially its applications on resource-limited platforms. Current segmentation models are trained and evaluated on massive highresolution scene images ("data level") and suffer from the expensive computation arising from the required multi-scale aggregation ("network level"). In both folds, the computational and energy costs in training and inference are notable due to the often desired large input resolutions and heavy computational burden of segmentation models. To this end, we propose DANCE, general automated DAta-Network Co-optimization for Efficient segmentation model training and inference. Distinct from existing efficient segmentation approaches that focus merely on light-weight network design, DANCE distinguishes itself as an automated simultaneous data-network co-optimization via both input data manipulation and network architecture slimming. Specifically, DANCE integrates automated data slimming which adaptively downsamples/drops input images and controls their corresponding contribution to the training loss guided by the images' spatial complexity. Such a downsampling operation, in addition to slimming down the cost associated with the input size directly, also shrinks the dynamic range of input object and context scales, therefore motivating us to also adaptively slim the network to match the downsampled data. Extensive experiments and ablating studies (on four SOTA segmentation models with three popular segmentation datasets under two training settings) demonstrate that DANCE can achieve "all-win" towards efficient segmentation (reduced training cost, less expensive inference, and better mean Intersection-over-Union (mIoU)). Specifically, DANCE can reduce ↓25% -↓77% energy consumption in training, ↓31% -↓56% in inference, while boosting the mIoU by ↓0.71% -↑ 13.34%. CCS Concepts: • Computing methodologies → Image segmentation; Neural networks; • Hardware → Platform power issues.

show abstract

CC-NET: Image Complexity Guided Network Compression for Biomedical Image Segmentation

Cited by 26 publications

References 37 publications

Open Source Iris Recognition Hardware and Software with Presentation Attack Detection

Open Source Iris Recognition Hardware and Software with Presentation Attack Detection

FCN-Based DenseNet Framework for Automated Detection and Classification of Skin Lesions in Dermoscopy Images

DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference

Contact Info

Product

Resources

About