# Loss Landscape Topology Reveals Why Simple Baselines are Competitive at 3D Point Cloud Segmentation Under Class Imbalance

Source: [Loss Landscape Topology Reveals Why Simple Baselines are Competitive at 3D Point Cloud Segmentation Under Class Imbalance](<https://www.sota2.com/research/paper/6a62f1b8ef5cfba72b498b62>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-08-05T05:00:12.726Z

Authors: Antonis Savva, Christos Kyrkou, Theocharis Theocharides

Published: 2026-07-23T09:19:31.000Z

## Abstract

Semantic segmentation of 3D point clouds faces severe class imbalance, yet the effectiveness of specialized imbalance-aware methods from 2D computer vision remains unclear in 3D contexts. We systematically evaluate 11 imbalance mitigation approaches across datasets with extreme (641:1) and moderate (56:1) imbalance ratios, revealing a surprising finding: standard cross-entropy with uniform weighting achieves competitive performance, typically within 0.8-3.3% mIoU of specialized methods across architectures and datasets. Through multifaceted mechanistic analysis of error patterns, decision boundaries, and the geometry of the optimization landscape, our analyses suggest that imbalance severity shapes the topology, creating narrow solution basins under extreme imbalance and flat plateaus under moderate imbalance. This appears to constrain the effectiveness of loss-level modifications, as all methods must navigate these geometric constraints. Our findings offer practical guidance; standard cross-entropy provides a robust baseline, with specialized methods offering modest improvements (0.8-3.3% mIoU) that vary by architecture and dataset but risk substantial degradation if poorly tuned. This work provides the first mechanistic explanation for why techniques proven effective in 2D do not readily transfer to point-based 3D point cloud segmentation, validated across two representative architectures.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2607.21089>)

[PDF](<https://arxiv.org/pdf/2607.21089.pdf>)
