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

• URL: http://arxiv.org/abs/2607.21089v1
• Date: Thu, 23 Jul 2026 09:19:31 GMT
• Title: Loss Landscape Topology Reveals Why Simple Baselines are Competitive at 3D Point Cloud Segmentation Under Class Imbalance
• Abstract summary: We evaluate 11 imbalance mitigation approaches across datasets with extreme and moderate imbalance ratios.<n>Standard cross-entropy with uniform weighting achieves competitive performance, typically within 0.8-3.3% mIoU.<n>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.
• Score: 5.276232626689568
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• How Sampling Strategy Affects Imbalance Mitigation in LiDAR Segmentation: A Study of Structured vs. Random Point-Based Architectures [5.276232626689568]
  Class imbalance in LiDAR point clouds poses challenges for semantic segmentation.<n>We benchmark six reweighting schemes and five imbalance-aware losses across three datasets.
  arXiv  Detail & Related papers  (2026-08-17T15:00:55Z)
• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• Articulating then Matching: Zero-Shot Shape Matching for Uncurated Data [0.5014513738509991]
  Finding dense correspondences between 3D shapes is a fundamental yet unresolved challenge, especially in real-world environments.<n>We present ATM, a framework that requires no correspondence-specific training and robustly addresses these issues at once.
  arXiv  Detail & Related papers  (2026-06-28T03:05:46Z)
• The Geometry of Robustness: Optimizing Loss Landscape Curvature and Feature Manifold Alignment for Robust Finetuning of Vision-Language Models [33.10473765967503]
  Generalization-preserving methods retain ID/OOD performance but leave models vulnerable to adversarial attacks.<n>Our key insight is that the robustness trade-off stems from two geometric failures: sharp, anisotropic minima in parameter space and unstable feature representations that deform under perturbation.<n>We propose GRACE, a unified fine-tuning framework that jointly regularizes the parameter-space curvature and feature-space invariance for VLMs.
  arXiv  Detail & Related papers  (2026-03-28T05:22:00Z)
• Test-Time Adaptation for Anomaly Segmentation via Topology-Aware Optimal Transport Chaining [10.091031517157411]
  TopoOT is a topology-aware optimal transport (OT) framework.<n>It integrates multi-filtration persistence diagrams (PDs) with test-time adaptation (TTA)<n>TopoOT achieves state-of-the-art performance across 2D and 3D anomaly detection benchmarks.
  arXiv  Detail & Related papers  (2026-01-28T07:49:28Z)
• 3D-ANC: Adaptive Neural Collapse for Robust 3D Point Cloud Recognition [21.95358957900039]
  We present 3D-ANC, a novel approach that capitalizes on the Neural Collapse (NC) mechanism to orchestrate discriminative feature learning.<n>We show that 3D-ANC significantly improves the robustness of models with various structures on two datasets.
  arXiv  Detail & Related papers  (2025-11-10T12:37:00Z)
• Zero-shot Inexact CAD Model Alignment from a Single Image [53.37898107159792]
  A practical approach to infer 3D scene structure from a single image is to retrieve a closely matching 3D model from a database and align it with the object in the image.<n>Existing methods rely on supervised training with images and pose annotations, which limits them to a narrow set of object categories.<n>We propose a weakly supervised 9-DoF alignment method for inexact 3D models that requires no pose annotations and generalizes to unseen categories.
  arXiv  Detail & Related papers  (2025-07-04T04:46:59Z)
• FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models [59.13757801286343]
  Few-shot class-incremental learning aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data.<n>We introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise.
  arXiv  Detail & Related papers  (2023-12-28T14:52:07Z)
• Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation [70.32536356351706]
  We introduce MRP-Net that constitutes a common deep network backbone with two output heads subscribing to two diverse configurations. We derive suitable measures to quantify prediction uncertainty at both pose and joint level. We present a comprehensive evaluation of the proposed approach and demonstrate state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-29T07:14:58Z)
• Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling [67.75095378830694]
  We develop a two-stage odometry estimation network, where we obtain the ego-motion by estimating a set of sub-region transformations. In this paper, we aim to alleviate the influence of unreliable structures in training, inference and mapping phases. Our two-frame odometry outperforms the previous state of the arts by 16%/12% in terms of translational/rotational errors.
  arXiv  Detail & Related papers  (2022-02-27T12:52:27Z)
• Dense Non-Rigid Structure from Motion: A Manifold Viewpoint [162.88686222340962]
  Non-Rigid Structure-from-Motion (NRSfM) problem aims to recover 3D geometry of a deforming object from its 2D feature correspondences across multiple frames. We show that our approach significantly improves accuracy, scalability, and robustness against noise.
  arXiv  Detail & Related papers  (2020-06-15T09:15:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.