Image de couverture de livre

Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wu, Qirui, Zhang, Shizhou, Cheng, De, Xing, Yinghui, Xu, Di, Wang, Peng, Zhang, Yanning
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Better Matching, Less Forgetting: A Quality-Guided Matcher for Transformer-based Incremental Object Detection
par: Wu, Qirui, et autres
Publié: (2026)

YOLO-IOD: Towards Real Time Incremental Object Detection
par: Zhang, Shizhou, et autres
Publié: (2025)

Knowing the Unknown: Interpretable Open-World Object Detection via Concept Decomposition Model
par: Lv, Xueqiang, et autres
Publié: (2026)

Visual Prompt Tuning in Null Space for Continual Learning
par: Lu, Yue, et autres
Publié: (2024)

Cross-Platform Video Person ReID: A New Benchmark Dataset and Adaptation Approach
par: Zhang, Shizhou, et autres
Publié: (2024)

Frequency-Guided Spatial Adaptation for Camouflaged Object Detection
par: Zhang, Shizhou, et autres
Publié: (2024)

CrossDiff: Exploring Self-Supervised Representation of Pansharpening via Cross-Predictive Diffusion Model
par: Xing, Yinghui, et autres
Publié: (2024)

MS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimization
par: Xing, Yinghui, et autres
Publié: (2023)

On Modality Incomplete Infrared-Visible Object Detection: An Architecture Compatibility Perspective
par: Yang, Shuo, et autres
Publié: (2025)

DuGI-MAE: Improving Infrared Mask Autoencoders via Dual-Domain Guidance
par: Xing, Yinghui, et autres
Publié: (2025)

Text-based Person Search in Full Images via Semantic-Driven Proposal Generation
par: Zhang, Shizhou, et autres
Publié: (2021)

Dual-Modal Prompting for Sketch-Based Image Retrieval
par: Gao, Liying, et autres
Publié: (2024)

MCF-VC: Mitigate Catastrophic Forgetting in Class-Incremental Learning for Multimodal Video Captioning
par: Xiong, Huiyu, et autres
Publié: (2024)

Reducing Catastrophic Forgetting in Online Class Incremental Learning Using Self-Distillation
par: Nagata, Kotaro, et autres
Publié: (2024)

Not Just Object, But State: Compositional Incremental Learning without Forgetting
par: Zhang, Yanyi, et autres
Publié: (2024)

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
par: Zhang, Hangtao, et autres
Publié: (2024)

Adaptive Spatial Augmentation for Semi-supervised Semantic Segmentation
par: Ran, Lingyan, et autres
Publié: (2025)

Defying Imbalanced Forgetting in Class Incremental Learning
par: Xu, Shixiong, et autres
Publié: (2024)

Balancing Stability and Plasticity in Pretrained Detector: A Dual-Path Framework for Incremental Object Detection
par: Li, Songze, et autres
Publié: (2025)

Make Domain Shift a Catastrophic Forgetting Alleviator in Class-Incremental Learning
par: Chen, Wei, et autres
Publié: (2024)

Mitigating Catastrophic Forgetting in the Incremental Learning of Medical Images
par: Yavari, Sara, et autres
Publié: (2025)

AdaSemiCD: An Adaptive Semi-Supervised Change Detection Method Based on Pseudo-Label Evaluation
par: Lingyan, Ran, et autres
Publié: (2024)

Attention Retention for Continual Learning with Vision Transformers
par: Lu, Yue, et autres
Publié: (2026)

A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gap
par: Zhang, Lijun, et autres
Publié: (2024)

SlowFastVAD: Video Anomaly Detection via Integrating Simple Detector and RAG-Enhanced Vision-Language Model
par: Ding, Zongcan, et autres
Publié: (2025)

Solving the Catastrophic Forgetting Problem in Generalized Category Discovery
par: Cao, Xinzi, et autres
Publié: (2025)

NIV-SSD: Neighbor IoU-Voting Single-Stage Object Detector From Point Cloud
par: Liu, Shuai, et autres
Publié: (2024)

Incremental Concept Formation over Visual Images Without Catastrophic Forgetting
par: Barari, Nicki, et autres
Publié: (2024)

MultIOD: Rehearsal-free Multihead Incremental Object Detector
par: Belouadah, Eden, et autres
Publié: (2023)

Deep Learning-Based Object Detection for Autonomous Vehicles: A Comparative Study of One-Stage and Two-Stage Detectors on Basic Traffic Objects
par: Karbouj, Bsher, et autres
Publié: (2026)

Textual Inversion for Efficient Adaptation of Open-Vocabulary Object Detectors Without Forgetting
par: Ruis, Frank, et autres
Publié: (2025)

Multimodal Task Representation Memory Bank vs. Catastrophic Forgetting in Anomaly Detection
par: Zhou, You, et autres
Publié: (2025)

MuseumMaker: Continual Style Customization without Catastrophic Forgetting
par: Liu, Chenxi, et autres
Publié: (2024)

Autoregressive Denoising Score Matching is a Good Video Anomaly Detector
par: Zhang, Hanwen, et autres
Publié: (2025)

Catastrophic Forgetting Mitigation via Discrepancy-Weighted Experience Replay
par: Xu, Xinrun, et autres
Publié: (2025)

StageInteractor: Query-based Object Detector with Cross-stage Interaction
par: Teng, Yao, et autres
Publié: (2023)

You Only Need Two Detectors to Achieve Multi-Modal 3D Multi-Object Tracking
par: Wang, Xiyang, et autres
Publié: (2023)

ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think
par: Feng, Tao, et autres
Publié: (2025)

ProtoFlow: Mitigating Forgetting in Class-Incremental Remote Sensing Segmentation via Low-Curvature Prototype Flow
par: Wu, Jiekai, et autres
Publié: (2026)

Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation
par: Bafghi, Reza Akbarian, et autres
Publié: (2025)