# Fast GraspNeXt: A Fast Self-Attention Neural Network Architecture for Multi-task Learning in Computer Vision Tasks for Robotic Grasping on the Edge

arXiv: https://arxiv.org/abs/2304.11196 · HTML: https://mlsanity.com/paper/2304.11196/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 15 references that are in the map.
- First posted on arXiv 21 Apr 2023.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling](https://mlsanity.com/paper/2109.11103/) (2021)
- [SuctionNet-1Billion: A Large-Scale Benchmark for Suction Grasping](https://mlsanity.com/paper/2103.12311/) (2021)
- [NetScore: Towards Universal Metrics for Large-scale Performance Analysis of Deep Neural Networks for Practical On-Device Edge Usage](https://mlsanity.com/paper/1806.05512/) (2018)
- [FermiNets: Learning generative machines to generate efficient neural networks via generative synthesis](https://mlsanity.com/paper/1809.05989/) (2018)
- [TinySpeech: Attention Condensers for Deep Speech Recognition Neural Networks on Edge Devices](https://mlsanity.com/paper/2008.04245/) (2020)
- [Dex-Net 3.0: Computing Robust Robot Vacuum Suction Grasp Targets in Point Clouds using a New Analytic Model and Deep Learning](https://mlsanity.com/paper/1709.06670/) (2017)
- [MetaGraspNet: A Large-Scale Benchmark Dataset for Scene-Aware Ambidextrous Bin Picking via Physics-based Metaverse Synthesis](https://mlsanity.com/paper/2208.03963/) (2022)
- [Improving Robotic Grasping on Monocular Images Via Multi-Task Learning and Positional Loss](https://mlsanity.com/paper/2011.02888/) (2020)

## Built on by (most cited first, 7 of 7)

- [Multi-Objective Optimization for Sparse Deep Multi-Task Learning](https://mlsanity.com/paper/2308.12243/) (2023)
- [TurboViT: Generating Fast Vision Transformers via Generative Architecture Search](https://mlsanity.com/paper/2308.11421/) (2023)
- [DVQI: A Multi-task, Hardware-integrated Artificial Intelligence System for Automated Visual Inspection in Electronics Manufacturing](https://mlsanity.com/paper/2312.09232/) (2023)
- [Robust Analysis of Multi-Task Learning Efficiency: New Benchmarks on Light-Weighed Backbones and Effective Measurement of Multi-Task Learning Challenges by Feature Disentanglement](https://mlsanity.com/paper/2402.03557/) (2024)
- [GCDance: Genre-Controlled Music-Driven 3D Full Body Dance Generation](https://mlsanity.com/paper/2502.18309/) (2025)
- [ILASH: A Predictive Neural Architecture Search Framework for Multi-Task Applications](https://mlsanity.com/paper/2412.02116/) (2024)
- [Sharper Risk Bound for Multi-Task Learning with Multi-Graph Dependent Data](https://mlsanity.com/paper/2502.18167/) (2025)

## Abstract (arXiv)

Multi-task learning has shown considerable promise for improving the performance of deep learning-driven vision systems for the purpose of robotic grasping. However, high architectural and computational complexity can result in poor suitability for deployment on embedded devices that are typically leveraged in robotic arms for real-world manufacturing and warehouse environments. As such, the design of highly efficient multi-task deep neural network architectures tailored for computer vision tasks for robotic grasping on the edge is highly desired for widespread adoption in manufacturing environments. Motivated by this, we propose Fast GraspNeXt, a fast self-attention neural network architecture tailored for embedded multi-task learning in computer vision tasks for robotic grasping. To build Fast GraspNeXt, we leverage a generative network architecture search strategy with a set of architectural constraints customized to achieve a strong balance between multi-task learning performance and embedded inference efficiency. Experimental results on the MetaGraspNet benchmark dataset show that the Fast GraspNeXt network design achieves the highest performance (average precision (AP), accuracy, and mean squared error (MSE)) across multiple computer vision tasks when compared to other efficient multi-task network architecture designs, while having only 17.8M parameters (about >5x smaller), 259 GFLOPs (as much as >5x lower) and as much as >3.15x faster on a NVIDIA Jetson TX2 embedded processor.