Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios

2025-06-30

AI Summary

To address generalization degradation, representation collapse, and catastrophic forgetting in object detection under dynamic environments—where the closed-set assumption fails—this paper proposes a continual test-time adaptation framework. Methodologically, it replaces conventional fine-tuning with an environment-aware parameter generation mechanism, introduces a dual-path LoRA-based domain-aware adapter for feature disentanglement, and incorporates a lightweight conditional diffusion model for parameter synthesis. Additionally, a class-center optimal transport alignment strategy is employed to mitigate cross-domain distribution shift and knowledge forgetting. The method updates only a minimal number of parameters while preserving backbone representation capacity. Evaluated on multiple continual domain adaptation detection benchmarks, it achieves state-of-the-art performance. Visualizations confirm that the synthesized parameters concentrate on semantically meaningful object features, yielding substantial improvements in generalization and stability.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

In practice, environments constantly change over time and space, posing significant challenges for object detectors trained based on a closed-set assumption, i.e., training and test data share the same distribution. To this end, continual test-time adaptation has attracted much attention, aiming to improve detectors' generalization by fine-tuning a few specific parameters, e.g., BatchNorm layers. However, based on a small number of test images, fine-tuning certain parameters may affect the representation ability of other fixed parameters, leading to performance degradation. Instead, we explore a new mechanism, i.e., converting the fine-tuning process to a specific-parameter generation. Particularly, we first design a dual-path LoRA-based domain-aware adapter that disentangles features into domain-invariant and domain-specific components, enabling efficient adaptation. Additionally, a conditional diffusion-based parameter generation mechanism is presented to synthesize the adapter's parameters based on the current environment, preventing the optimization from getting stuck in local optima. Finally, we propose a class-centered optimal transport alignment method to mitigate catastrophic forgetting. Extensive experiments conducted on various continuous domain adaptive object detection tasks demonstrate the effectiveness. Meanwhile, visualization results show that the representation extracted by the generated parameters can capture more object-related information and strengthen the generalization ability.

Problem

• Adapt object detectors to dynamic environments efficiently
• Generate specific parameters to avoid performance degradation
• Mitigate catastrophic forgetting in continual adaptation scenarios

Innovation

• Dual-path LoRA adapter for feature disentanglement
• Conditional diffusion for parameter generation
• Class-centered optimal transport alignment