Scale Invariant Fully Convolutional Network: Detecting Hands Efficiently

Liú, Dan; Du, Dawei; Zhang, Libo; Luo, Tiejian; Wu, Yicheng; Huang, Feiyue; Lyu, Siwei

doi:10.1609/aaai.v33i01.33014344

Cited by 5 publications

(2 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, multi-branch networks have been proposed, where each branch has its own filter and scale, leading to a model where different scales are handle and combined for the final prediction [49]. Multi-scale pyramidal models with skip layers to allow the combination of large and small scale information have been successful [44,33] and used for general object detection tasks with the RCNN [43]. Moreover, invariances can induce symmetries that are efficient methods to reduce the number of parameters [27].…”

Section: Related Workmentioning

confidence: 99%

Scale dependant layer for self-supervised nuclei encoding

Naylor¹,

Tsai²,

Laé³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent developments in self-supervised learning give us the possibility to further reduce human intervention in multi-step pipelines where the focus evolves around particular objects of interest. In the present paper, the focus lays in the nuclei in histopathology images. In particular we aim at extracting cellular information in an unsupervised manner for a downstream task. As nuclei present themselves in a variety of sizes, we propose a new Scale-dependant convolutional layer to bypass scaling issues when resizing nuclei. On three nuclei datasets, we benchmark the following methods: handcrafted, pre-trained ResNet, supervised ResNet and self-supervised features. We show that the proposed convolution layer boosts performance and that this layer combined with Barlows-Twins allows for better nuclei encoding compared to the supervised paradigm in the low sample setting and outperforms all other proposed unsupervised methods. In addition, we extend the existing TNBC dataset to incorporate nuclei class annotation in order to enrich and publicly release a small sample setting dataset for nuclei segmentation and classification.

show abstract

Section: Related Workmentioning

confidence: 99%

Scale dependant layer for self-supervised nuclei encoding

Naylor¹,

Tsai²,

Laé³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Part of the work has been introduced in [23]. The extensions made in this article compared to [23] The main contributions of this paper are in four folds:…”

Section: Introductionmentioning

confidence: 99%

Towards interpretable and robust hand detection via pixel-wise prediction

Liú

Zhang

Luo

et al. 2020

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

The lack of interpretability of existing CNN-based hand detection methods makes it difficult to understand the rationale behind their predictions. In this paper, we propose a novel neural network model, which introduces interpretability into hand detection for the first time. The main improvements include: (1) Detect hands at pixel level to explain what pixels are the basis for its decision and improve transparency of the model. (2) The explainable Highlight Feature Fusion block highlights distinctive features among multiple layers and learns discriminative ones to gain robust performance. (3) We introduce a transparent representation, the rotation map, to learn rotation features instead of complex and non-transparent rotation and derotation layers. (4) Auxiliary supervision accelerates the training process, which saves more than 10 hours in our experiments. Experimental results on the VIVA and Oxford hand detection and tracking datasets show competitive accuracy of our method compared with state-of-the-art methods with higher speed. (Libo Zhang)1 Dan Liu and Tiejian Luo were contributed equally and should be considered as co-first authors. Models and code are available at https://isrc.iscas.ac.cn/gitlab/research/pr2020phdn.

show abstract

Deep Object Detector With Attentional Spatiotemporal LSTM for Space Human–Robot Interaction

Gao

Chen

et al. 2022

IEEE Trans. Human-Mach. Syst.

View full text Add to dashboard Cite

Scale Invariant Fully Convolutional Network: Detecting Hands Efficiently

Cited by 5 publications

References 25 publications

Scale dependant layer for self-supervised nuclei encoding

Scale dependant layer for self-supervised nuclei encoding

Towards interpretable and robust hand detection via pixel-wise prediction

Deep Object Detector With Attentional Spatiotemporal LSTM for Space Human–Robot Interaction

Contact Info

Product

Resources

About