CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation

• URL: http://arxiv.org/abs/2502.17429v1
• Date: Mon, 24 Feb 2025 18:58:58 GMT
• Title: CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation
• Authors: Vishal Thengane, Jean Lahoud, Hisham Cholakkal, Rao Muhammad Anwer, Lu Yin, Xiatian Zhu, Salman Khan,
• Abstract summary: Current methods struggle to address realistic scenarios where new categories emerge over time with natural class imbalance.<n>We propose a framework to tackle both textbfContinual textbfLearning and class textbfImbalance for textbf3D instance segmentation.<n>Our proposed approach combines Exemplar Replay (ER), Knowledge Distillation (KD), and a novel Imbalance Correction (IC) module.
• Score: 67.36817440834251
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While 3D instance segmentation has made significant progress, current methods struggle to address realistic scenarios where new categories emerge over time with natural class imbalance. This limitation stems from existing datasets, which typically feature few well-balanced classes. Although few datasets include unbalanced class annotations, they lack the diverse incremental scenarios necessary for evaluating methods under incremental settings. Addressing these challenges requires frameworks that handle both incremental learning and class imbalance. However, existing methods for 3D incremental segmentation rely heavily on large exemplar replay, focusing only on incremental learning while neglecting class imbalance. Moreover, frequency-based tuning for balanced learning is impractical in these setups due to the lack of prior class statistics. To overcome these limitations, we propose a framework to tackle both \textbf{C}ontinual \textbf{L}earning and class \textbf{Imb}alance for \textbf{3D} instance segmentation (\textbf{CLIMB-3D}). Our proposed approach combines Exemplar Replay (ER), Knowledge Distillation (KD), and a novel Imbalance Correction (IC) module. Unlike prior methods, our framework minimizes ER usage, with KD preventing forgetting and supporting the IC module in compiling past class statistics to balance learning of rare classes during incremental updates. To evaluate our framework, we design three incremental scenarios based on class frequency, semantic similarity, and random grouping that aim to mirror real-world dynamics in 3D environments. Experimental results show that our proposed framework achieves state-of-the-art performance, with an increase of up to 16.76\% in mAP compared to the baseline. Code will be available at: \href{https://github.com/vgthengane/CLIMB3D}{https://github.com/vgthengane/CLIMB3D}

Related papers

• Covariance-based Space Regularization for Few-shot Class Incremental Learning [25.435192867105552]
  Few-shot Class Incremental Learning (FSCIL) requires the model to continually learn new classes with limited labeled data. Due to the limited data in incremental sessions, models are prone to overfitting new classes and suffering catastrophic forgetting of base classes. Recent advancements resort to prototype-based approaches to constrain the base class distribution and learn discriminative representations of new classes.
  arXiv  Detail & Related papers  (2024-11-02T08:03:04Z)
• TeFF: Tracking-enhanced Forgetting-free Few-shot 3D LiDAR Semantic Segmentation [10.628870775939161]
  This paper addresses the limitations of current few-shot semantic segmentation by exploiting the temporal continuity of LiDAR data. We employ a tracking model to generate pseudo-ground-truths from a sequence of LiDAR frames, enhancing the dataset's ability to learn on novel classes. We incorporate LoRA, a technique that reduces the number of trainable parameters, thereby preserving the model's performance on base classes while improving its adaptability to novel classes.
  arXiv  Detail & Related papers  (2024-08-28T09:18:36Z)
• OrCo: Towards Better Generalization via Orthogonality and Contrast for Few-Shot Class-Incremental Learning [57.43911113915546]
  Few-Shot Class-Incremental Learning (FSCIL) introduces a paradigm in which the problem space expands with limited data. FSCIL methods inherently face the challenge of catastrophic forgetting as data arrives incrementally. We propose the OrCo framework built on two core principles: features' orthogonality in the representation space, and contrastive learning.
  arXiv  Detail & Related papers  (2024-03-27T13:30:48Z)
• Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection [111.0991686509715]
  We study the class imbalance problem for semi-supervised object detection (SSOD) under more challenging scenarios. We propose a simple yet effective gradient-based sampling framework that tackles the class imbalance problem from the perspective of two types of confirmation biases. Experiments on three proposed sub-tasks, namely MS-COCO, MS-COCO to Object365 and LVIS, suggest that our method outperforms current class imbalanced object detectors by clear margins.
  arXiv  Detail & Related papers  (2024-03-22T11:30:10Z)
• Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants [166.916517335816]
  In this paper, we offer a unified solution to the misalignment dilemma in the three tasks. We propose neural collapse terminus that is a fixed structure with the maximal equiangular inter-class separation for the whole label space. Our method holds the neural collapse optimality in an incremental fashion regardless of data imbalance or data scarcity.
  arXiv  Detail & Related papers  (2023-08-03T13:09:59Z)
• Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling [38.07637524378327]
  Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection. Existing DA methods suffer from a substantial drop in performance when applied to a multi-class training setting. We propose a novel ReDB framework tailored for learning to detect all classes at once.
  arXiv  Detail & Related papers  (2023-07-16T04:34:11Z)
• S3C: Self-Supervised Stochastic Classifiers for Few-Shot Class-Incremental Learning [22.243176199188238]
  Few-shot class-incremental learning (FSCIL) aims to learn progressively about new classes with very few labeled samples, without forgetting the knowledge of already learnt classes. FSCIL suffers from two major challenges: (i) over-fitting on the new classes due to limited amount of data, (ii) catastrophically forgetting about the old classes due to unavailability of data from these classes in the incremental stages.
  arXiv  Detail & Related papers  (2023-07-05T12:41:46Z)
• Constrained Few-shot Class-incremental Learning [14.646083882851928]
  Continually learning new classes from fresh data without forgetting previous knowledge of old classes is a very challenging research problem. We propose C-FSCIL, which is architecturally composed of a frozen meta-learned feature extractor, a trainable fixed-size fully connected layer, and a rewritable dynamically growing memory. C-FSCIL provides three update modes that offer a trade-off between accuracy and compute-memory cost of learning novel classes.
  arXiv  Detail & Related papers  (2022-03-30T18:19:36Z)
• Modality-Aware Triplet Hard Mining for Zero-shot Sketch-Based Image Retrieval [51.42470171051007]
  This paper tackles the Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) problem from the viewpoint of cross-modality metric learning. By combining two fundamental learning approaches in DML, e.g., classification training and pairwise training, we set up a strong baseline for ZS-SBIR. We show that Modality-Aware Triplet Hard Mining (MATHM) enhances the baseline with three types of pairwise learning.
  arXiv  Detail & Related papers  (2021-12-15T08:36:44Z)
• Improving Calibration for Long-Tailed Recognition [68.32848696795519]
  We propose two methods to improve calibration and performance in such scenarios. For dataset bias due to different samplers, we propose shifted batch normalization. Our proposed methods set new records on multiple popular long-tailed recognition benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-01T13:55:21Z)

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.