We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data. We represent these edges as a collection of parametric curves (i.e., lines, circles, and B-splines).

We executed these methods for 20 iterations each having 200 testing samples. We report the mean and standard deviation of the number of counterexamples discovered.

Larger transformer models always perform better on various tasks but require more costs to scale up the model size. To efficiently enlarge models, the mixture-ofexperts (MoE) architecture is widely adopted, which consists of a gate network and a series of experts and keep the training cost constant by routing the input data to a fixed number of experts instead of all. In existing large-scale MoE training systems, experts would be distributed among different GPUs for parallelization, and thus input data requires additional all-to-all communications to access the target experts and conduct corresponding computations. However, upon evaluating the training process of three mainstream MoE models on commonly used GPU clusters, we found that the all-to-all communication ratio averaged around 45%, which significantly hinders the efficiency and scalability of training MoE models. In this paper, we propose LSH-MoE, a communication-efficient MoE training framework using locality-sensitive hashing (LSH). We first present the problems of scaling MoE training in existing systems and highlight the potential of exploiting token similarity to facilitate data compression. Then, we introduce an efficient LSH-based compression technique, which utilizes the cross-polytope hashing for rapid clustering and implements a residual-based error compensation scheme to alleviate the adverse impact of compression. To verify the effectiveness of our methods, we conduct experiments on both language models (e.g., RoBERTa, GPT, and T5) and vision models (e.g., Swin) for pre-training and fine-tuning tasks. The results demonstrate that our method substantially outperforms its counterparts across different tasks by 1.28 - 2.2 of speedup.

Josie Gotz is a Senior Research Engineer in the Intelligent Robotics Team at the Manufacturing Technology Centre. She works as the technical lead on a variety of robotics and automation projects from research and development through to integration across a wide variety of manufacturing sectors. She specialises in creating innovative solutions for these industries, combining vision systems and artificial intelligence to build flexible automation systems. Josie has a particular interest in automated disassembly for material recovery, reuse and recycling.

In this supplementary material, following sections are discussed: we include training algorithm (Sec. We show the impact on performance of our method with different dropout (spatial [6]) rates in Tab. 1. Our method mostly retains performance when perturbing the dropout rate from 10% to 30%. In particular, we see a maximum decrease of 0.8% in mAP score when increasing the dropout rate from 10% to 30%. This is expected as increasing the dropout rate increases prediction uncertainty which in turn affects the pseudo-label selection.