Point-Selection Fine-Tuning Framework for Robust Point Cloud Classification
Noisy and corrupted points can substantially degrade point cloud recognition performance, especially under challenging corruption settings. In particular, full fine-tuning of 3D pre-trained models may amplify the influence of outliers and overwrite robustness priors learned during pre-training, while naive parameter-efficient adaptation remains sensitive to corrupted tokens. To address this issue, we propose PSFT, a point-selection fine-tuning framework that improves robustness while remaining parameter-efficient. PSFT first estimates point-wise influence from pre-pooling features and adaptively retains minimally influential points to suppress outliers. Based on the selected subset, a prompt generation branch predicts layer-wise prompt tokens and injects them into a frozen backbone for lightweight downstream adaptation. To further mitigate residual noise after selection, we append a lightweight feature filter with bottleneck MLP transformation and Beta-gated residual blending to refine patch-token representations before prediction. Extensive experiments show that PSFT consistently reduces corruption error on ModelNet-C and ModelNet40-C across all tested 3D pre-trained backbones, while achieving the strongest ScanObjectNN-C results with ULIP-2 and Uni3D-B among the evaluated tuning strategies. Our implementation can be found at https://github.com/CVChMA/PSFT/tree/master.
Code (0)
등록된 구현이 없습니다.
Tasks
Point Cloud ClassificationSimilar Papers 제목 키워드 기반
PointLoRA: Low-Rank Adaptation with Token Selection for Point Cloud Learning
Self-supervised representation learning for point cloud has demonstrated effectiveness in improving pre-trained model performance across diverse tasks. However, as pre-trained models grow in complexity, fully fine-tuning…
parameter-efficient fine-tuningRepresentation LearningTSDS: Data Selection for Task-Specific Model Finetuning
Finetuning foundation models for specific tasks is an emerging paradigm in modern machine learning. The efficacy of task-specific finetuning largely depends on the selection of appropriate training data. We present TSDS …
Density EstimationDynamic Jointly Batch Selection for Data Efficient Machine Translation Fine-Tuning
Data quality and its effective selection are fundamental to improving the performance of machine translation models, serving as cornerstones for achieving robust and reliable translation systems. This paper presents a da…
Computational EfficiencyMachine TranslationRICo: Refined In-Context Contribution for Automatic Instruction-Tuning Data Selection
Data selection for instruction tuning is crucial for improving the performance of large language models (LLMs) while reducing training costs. In this paper, we propose Refined Contribution Measurement with In-Context Lea…
In-Context LearningInductive BiasUncertainty-Guided Checkpoint Selection for Reinforcement Finetuning of Large Language Models
Reinforcement learning (RL) finetuning is crucial to aligning large language models (LLMs), but the process is notoriously unstable and exhibits high variance across model checkpoints. In practice, selecting the best che…
Reinforcement Learning