# DcnnGrasp: Towards Accurate Grasp Pattern Recognition with Adaptive Regularizer Learning

arXiv: https://arxiv.org/abs/2205.05218 · HTML: https://mlsanity.com/paper/2205.05218/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 11 May 2022.

## Builds on (most cited first, 21 of 21)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [Recent Advances in Convolutional Neural Networks](https://mlsanity.com/paper/1512.07108/) (2015)
- [Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation](https://mlsanity.com/paper/1707.03374/) (2017)
- [Robust Imitation of Diverse Behaviors](https://mlsanity.com/paper/1707.02747/) (2017)
- [Macro F1 and Macro F1](https://mlsanity.com/paper/1911.03347/) (2019)
- [Robotic Grasp Detection using Deep Convolutional Neural Networks](https://mlsanity.com/paper/1611.08036/) (2016)
- [Multimodal Fusion of EMG and Vision for Human Grasp Intent Inference in Prosthetic Hand Control](https://mlsanity.com/paper/2104.03893/) (2021)
- [Vision-based Robotic Grasping From Object Localization, Object Pose Estimation to Grasp Estimation for Parallel Grippers: A Review](https://mlsanity.com/paper/1905.06658/) (2019)
- [Towards Creating a Deployable Grasp Type Probability Estimator for a Prosthetic Hand](https://mlsanity.com/paper/2101.05357/) (2021)
- [SAFARI: Safe and Active Robot Imitation Learning with Imagination](https://mlsanity.com/paper/2011.09586/) (2020)
- [LightLayers: Parameter Efficient Dense and Convolutional Layers for Image Classification](https://mlsanity.com/paper/2101.02268/) (2021)
- [NetCut: Real-Time DNN Inference Using Layer Removal](https://mlsanity.com/paper/2101.05363/) (2021)
- [Modeling Grasp Motor Imagery through Deep Conditional Generative Models](https://mlsanity.com/paper/1701.03041/) (2017)
- [Grasp Type Estimation for Myoelectric Prostheses using Point Cloud Feature Learning](https://mlsanity.com/paper/1908.02564/) (2019)
- [From Hand-Perspective Visual Information to Grasp Type Probabilities: Deep Learning via Ranking Labels](https://mlsanity.com/paper/2103.04863/) (2021)
- [SmartHand: Towards Embedded Smart Hands for Prosthetic and Robotic Applications](https://mlsanity.com/paper/2107.14598/) (2021)

## Abstract (arXiv)

The task of grasp pattern recognition aims to derive the applicable grasp types of an object according to the visual information. Current state-of-the-art methods ignore category information of objects which is crucial for grasp pattern recognition. This paper presents a novel dual-branch convolutional neural network (DcnnGrasp) to achieve joint learning of object category classification and grasp pattern recognition. DcnnGrasp takes object category classification as an auxiliary task to improve the effectiveness of grasp pattern recognition. Meanwhile, a new loss function called joint cross-entropy with an adaptive regularizer is derived through maximizing a posterior, which significantly improves the model performance. Besides, based on the new loss function, a training strategy is proposed to maximize the collaborative learning of the two tasks. The experiment was performed on five household objects datasets including the RGB-D Object dataset, Hit-GPRec dataset, Amsterdam library of object images (ALOI), Columbia University Image Library (COIL-100), and MeganePro dataset 1. The experimental results demonstrated that the proposed method can achieve competitive performance on grasp pattern recognition with several state-of-the-art methods. Specifically, our method even outperformed the second-best one by nearly 15% in terms of global accuracy for the case of testing a novel object on the RGB-D Object dataset.