Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection

• URL: http://arxiv.org/abs/2607.14560v1
• Date: Thu, 16 Jul 2026 04:39:35 GMT
• Title: Breaking the Model Forgetting Cycle in Long-Incremental 3D Object Detection
• Abstract summary: Incremental 3D object detection requires a detector to learn novel object classes while remembering previously learned ones over sequentially arriving data.<n>Previous methods, primarily based on pseudo-labeling, perform reasonably in short-incremental stages but still suffer from severe model forgetting when dealing with long-incremental sequences.<n>We propose the emphLearning-Dynamics-driven Memory and Review framework to address this issue.
• Score: 17.58819091362561
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Incremental 3D object detection requires a detector to learn novel object classes while remembering previously learned ones over sequentially arriving data. Previous methods, primarily based on pseudo-labeling, perform reasonably in short-incremental stages but still suffer from severe model forgetting when dealing with long-incremental sequences. We investigate this failure and reveal a detrimental self-reinforcing cycle: data distribution shift of novel classes causes model forgetting on old classes, which further produces accumulated error in pseudo-labeling that exacerbates model degradation. To address this issue, we draw inspiration from the human learning process and propose the \emph{Learning-Dynamics-driven Memory and Review} (LDMR) framework. LDMR monitors per-class detection quality at periodic training checkpoints and uses these learning-dynamics signals to drive two innovative mechanisms, namely (i) human-like intra-stage review that divides each incremental stage into multiple sub-stages' training and concentrates on remembering the most-forgotten objects, and (ii) scene-aware cross-stage memory evolution that evolves a memory bank to transfer knowledge between two consecutive stages by jointly considering scene learnability and diversity. Extensive experiments across multiple long-incremental protocols on indoor benchmarks SUN RGB-D and ScanNetV2 show that LDMR substantially mitigates the model forgetting and outperforms all baselines by a clear margin. Code is available at https://github.com/qianpeisheng/LDMR.

Related papers

• Open-Vocabulary 3D Object Detection with Co-Distillation Discovery and Dual Guidance Robust Training [15.510191654885778]
  3D object detection has gained increasing attention for its ability to detect unseen objects in 3D scenes.<n>Existing approaches typically adopt a two-stage pipeline that first discovers novel objects using foundation models and then trains a 3D-OVD model based on these discovered objects.<n>We advocate for improving both the reliability of novel object discovery and the robustness of model training, and propose an innovative framework.
  arXiv  Detail & Related papers  (2026-08-20T12:47:40Z)
• STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detection [26.581594459769363]
  Traditional detectors often forget previously learned categories when learning new ones.<n>Existing methods largely overlook the intra-class scale variations prevalent in remote sensing scenes.<n>We propose a novel framework, STAR-IOD, to address these challenges.
  arXiv  Detail & Related papers  (2026-05-20T05:43:09Z)
• 4D Contrastive Superflows are Dense 3D Representation Learners [62.433137130087445]
  We introduce SuperFlow, a novel framework designed to harness consecutive LiDAR-camera pairs for establishing pretraining objectives. To further boost learning efficiency, we incorporate a plug-and-play view consistency module that enhances alignment of the knowledge distilled from camera views.
  arXiv  Detail & Related papers  (2024-07-08T17:59:54Z)
• 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)
• Augment and Criticize: Exploring Informative Samples for Semi-Supervised Monocular 3D Object Detection [64.65563422852568]
  We improve the challenging monocular 3D object detection problem with a general semi-supervised framework. We introduce a novel, simple, yet effective Augment and Criticize' framework that explores abundant informative samples from unlabeled data. The two new detectors, dubbed 3DSeMo_DLE and 3DSeMo_FLEX, achieve state-of-the-art results with remarkable improvements for over 3.5% AP_3D/BEV (Easy) on KITTI.
  arXiv  Detail & Related papers  (2023-03-20T16:28:15Z)
• SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection [108.57862846523858]
  We revisit the self-supervised multi-task learning framework, proposing several updates to the original method. We modernize the 3D convolutional backbone by introducing multi-head self-attention modules. In our attempt to further improve the model, we study additional self-supervised learning tasks, such as predicting segmentation maps.
  arXiv  Detail & Related papers  (2022-07-16T19:25:41Z)
• Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection [71.18882803642526]
  Deep learning approaches have shown remarkable performance in the 3D object detection task. They suffer from a catastrophic performance drop when incrementally learning new classes without revisiting the old data. This "catastrophic forgetting" phenomenon impedes the deployment of 3D object detection approaches in real-world scenarios. We present the first solution - SDCoT, a novel static-dynamic co-teaching method.
  arXiv  Detail & Related papers  (2021-12-14T09:03:41Z)
• Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection [54.92703325989853]
  We propose a two-stage Activation-to-Saliency (A2S) framework that effectively generates high-quality saliency cues. No human annotations are involved in our framework during the whole training process. Our framework reports significant performance compared with existing USOD methods.
  arXiv  Detail & Related papers  (2021-12-07T11:54:06Z)
• Towards Generalized and Incremental Few-Shot Object Detection [9.033533653482529]
  A novel Incremental Few-Shot Object Detection (iFSOD) method is proposed to enable the effective continual learning from few-shot samples. Specifically, a Double-Branch Framework (DBF) is proposed to decouple the feature representation of base and novel (few-shot) class. We conduct experiments on both Pascal VOC and MS-COCO, which demonstrate that our method can effectively solve the problem of incremental few-shot detection.
  arXiv  Detail & Related papers  (2021-09-23T12:38:09Z)
• Multi-View Correlation Distillation for Incremental Object Detection [12.536640582318949]
  We propose a novel textbfMulti-textbfView textbfCorrelation textbfDistillation (MVCD) based incremental object detection method.
  arXiv  Detail & Related papers  (2021-07-05T04:36:33Z)
• Two-Level Residual Distillation based Triple Network for Incremental Object Detection [21.725878050355824]
  We propose a novel incremental object detector based on Faster R-CNN to continuously learn from new object classes without using old data. It is a triple network where an old model and a residual model as assistants for helping the incremental model learning on new classes without forgetting the previous learned knowledge.
  arXiv  Detail & Related papers  (2020-07-27T11:04:57Z)
• Convolutional Tensor-Train LSTM for Spatio-temporal Learning [116.24172387469994]
  We propose a higher-order LSTM model that can efficiently learn long-term correlations in the video sequence. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. Our results achieve state-of-the-art performance-art in a wide range of applications and datasets.
  arXiv  Detail & Related papers  (2020-02-21T05:00:01Z)

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.