In the context of robotic grasping, object segmentation encounters several
difficulties when faced with dynamic conditions such as real-time operation,
occlusion, low lighting, motion blur, and object size variability. In response
to these challenges, we propose the Graph Mixer Neural Network that includes a
novel collaborative contextual mixing layer, applied to 3D event graphs formed
on asynchronous events. The proposed layer is designed to spread spatiotemporal
correlation within an event graph at four nearest neighbor levels parallelly.
We evaluate the effectiveness of our proposed method on the Event-based
Segmentation (ESD) Dataset, which includes five unique image degradation
challenges, including occlusion, blur, brightness, trajectory, scale variance,
and segmentation of known and unknown objects. The results show that our
proposed approach outperforms state-of-the-art methods in terms of mean
intersection over the union and pixel accuracy. Code available at:
this https URL

本文提出了一种名为 Graph Mixer Neural Network 的算法，采用协同上下文混合层来解决动态条件下物体分割遇到的挑战。本方法在事件图上应用，并通过四个最近邻层级并行地传播了时空相关性。实验表明该方法表现优于最先进的方法。

基于异步事件的全景分割的图混合神经网络

Asynchronous Events-based Panoptic Segmentation using Graph Mixer Neural  Network

Long-range dependencies modeling, widely used in capturing spatiotemporal
correlation, has shown to be effective in CNN dominated computer vision tasks.
Yet neither stacks of convolutional operations to enlarge receptive fields nor
recent nonlocal modules is computationally efficient. In this paper, we present
a generic family of lightweight global descriptors for modeling the
interactions between positions across different dimensions (e.g., channels,
frames). This descriptor enables subsequent convolutions to access the
informative global features with negligible computational complexity and
parameters. Benchmark experiments show that the proposed method can complete
state-of-the-art long-range mechanisms with a significant reduction in extra
computing cost. Code available at
this https URL

本文提出一种轻量级全局描述符，以建模跨不同维度（如通道、帧）之间的位置交互作用，使得后续卷积能够合理地访问此全局特征，从而在计算成本和参数数量上有了巨大的降低，也完成了最有效的长距离机制。