Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection

• URL: http://arxiv.org/abs/2607.17340v1
• Date: Sun, 19 Jul 2026 17:02:15 GMT
• Title: Orthogonal Knowledge Refreshing for Domain-Incremental Object Detection
• Abstract summary: Domain-incremental object detection requires models to continually adapt to new domains while preserving prior knowledge.<n>We propose Orthogonal Knowledge Refreshing (OKR), a simple yet effective framework for DIOD.<n>OKR incrementally constructs independent domain-specific subspaces via dedicated low-rank branches for each domain.
• Score: 37.885906679929796
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Domain-incremental object detection (DIOD) requires models to continually adapt to new domains while preserving prior knowledge. Recently, parameter-efficient fine-tuning offers a promising avenue, wherein a pre-trained model is frozen and a small number of learnable parameters are injected for downstream tasks. However, these methods risk overwriting critical past knowledge, triggering inter-domain interference and performance degradation. To address this challenge, we propose Orthogonal Knowledge Refreshing (OKR), a simple yet effective framework for DIOD. OKR incrementally constructs independent domain-specific subspaces via dedicated low-rank branches for each domain, which are seamlessly fused for a holistic decision, enabling conflict-free capacity expansion without domain selection during inference. To minimize knowledge interference during fusion, we present a gradient-based orthogonal refreshing strategy that projects gradient updates of new domains onto the orthogonal complement of the fused historical subspace, supporting continual adaptation without forgetting. Moreover, to mitigate semantic fragmentation across domains, we enforce topology-aware consistency, aligning the semantic structures of old and new domains. Extensive experiments validate the superiority of OKR, outperforming the best exemplar-free method by significant margins of +5.6% and +6.5% mAP on the Pascal VOC and BDD100K series, respectively.

Related papers

• Parameter isolation with domain-specific experts for incremental audio classification [4.541172620857825]
  This paper proposes a new domain-specific parameter-isolation architecture that retains all past domains.<n>We incorporate data-free generative replay to reconstruct previous-domain data and cross-domain feature generation to recover later expert features missing from earlier domains.<n>We achieve micro and macro accuracies of 78.4% and 78.9%, respectively, representing increases of 33 and 25 percentage points over the Challenge baseline.
  arXiv  Detail & Related papers  (2026-09-13T18:47:01Z)
• A Turn Toward Better Alignment: Few-Shot Generative Adaptation with Equivariant Feature Rotation [67.2019317630466]
  Few-shot image generation aims to effectively adapt a source generative model to a target domain using very few training images.<n>We propose Equivariant Feature Rotation (EFR), a novel adaptation strategy that aligns source and target domains at two complementary levels.<n>Our method significantly enhances the generative performance within the targeted domain.
  arXiv  Detail & Related papers  (2025-12-24T13:48:22Z)
• Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation [50.831196928686104]
  We propose a class-aware domain Knowledge Fusion and Fission method for continual test-time adaptation.<n>A domain Knowledge FIssion (KFI) module is designed to adaptively separate new domain knowledge from a paired class-aware domain prompt pool.<n>A domain Knowledge FUsion (KFU) module is further designed to merge the fissioned new knowledge into the existing knowledge pool with minimal cost.
  arXiv  Detail & Related papers  (2025-10-14T05:09:50Z)
• RoGA: Towards Generalizable Deepfake Detection through Robust Gradient Alignment [13.327130030147565]
  We propose a novel learning objective that aligns generalization gradient updates with ERM gradient updates.<n>The key innovation is the application of perturbations to model parameters, aligning the ascending points across domains.<n> Experimental results on multiple challenging deepfake detection datasets demonstrate that our gradient alignment strategy outperforms state-of-the-art domain generalization techniques.
  arXiv  Detail & Related papers  (2025-05-27T03:02:21Z)
• Dynamic Prompt Allocation and Tuning for Continual Test-Time Adaptation [29.931721498877483]
  Continual test-time adaptation (CTTA) has recently emerged to adapt to continuously evolving target distributions.<n>Existing methods typically incorporate explicit regularization terms to constrain the variation of model parameters.<n>We introduce learnable domain-specific prompts that guide the model to adapt to corresponding target domains.
  arXiv  Detail & Related papers  (2024-12-12T14:24:04Z)
• Gradient Alignment for Cross-Domain Face Anti-Spoofing [26.517887637150594]
  We introduce GAC-FAS, a novel learning objective that encourages the model to converge towards an optimal flat minimum. Unlike conventional sharpness-aware minimizers, GAC-FAS identifies ascending points for each domain and regulates the generalization gradient updates. We demonstrate the efficacy of GAC-FAS through rigorous testing on challenging cross-domain FAS datasets.
  arXiv  Detail & Related papers  (2024-02-29T02:57:44Z)
• Decompose to Adapt: Cross-domain Object Detection via Feature Disentanglement [79.2994130944482]
  We design a Domain Disentanglement Faster-RCNN (DDF) to eliminate the source-specific information in the features for detection task learning. Our DDF method facilitates the feature disentanglement at the global and local stages, with a Global Triplet Disentanglement (GTD) module and an Instance Similarity Disentanglement (ISD) module. By outperforming state-of-the-art methods on four benchmark UDA object detection tasks, our DDF method is demonstrated to be effective with wide applicability.
  arXiv  Detail & Related papers  (2022-01-06T05:43:01Z)
• Domain Conditioned Adaptation Network [90.63261870610211]
  We propose a Domain Conditioned Adaptation Network (DCAN) to excite distinct convolutional channels with a domain conditioned channel attention mechanism. This is the first work to explore the domain-wise convolutional channel activation for deep DA networks.
  arXiv  Detail & Related papers  (2020-05-14T04:23:24Z)
• Towards Stable and Comprehensive Domain Alignment: Max-Margin Domain-Adversarial Training [38.12978698952838]
  We propose a novel Max-margin Domain-Adversarial Training (MDAT) by designing an Adversarial Reconstruction Network (ARN) ARN conducts both feature-level and pixel-level domain alignment without involving extra network structures. Our approach outperforms other state-of-the-art domain alignment methods.
  arXiv  Detail & Related papers  (2020-03-30T07:48:52Z)
• Bi-Directional Generation for Unsupervised Domain Adaptation [61.73001005378002]
  Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. Conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure. We propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains.
  arXiv  Detail & Related papers  (2020-02-12T09:45:39Z)

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.