DCA: Dividing and Conquering Amnesia in Incremental Object Detection

• URL: http://arxiv.org/abs/2503.15295v1
• Date: Wed, 19 Mar 2025 15:17:14 GMT
• Title: DCA: Dividing and Conquering Amnesia in Incremental Object Detection
• Authors: Aoting Zhang, Dongbao Yang, Chang Liu, Xiaopeng Hong, Miao Shang, Yu Zhou,
• Abstract summary: We study the cause of forgetting and discover forgetting imbalance between localization and recognition in transformer-based IOD.<n>We propose a Divide-and-Conquer Amnesia (DCA) strategy, which redesigns the transformer-based IOD into a localization-then-recognition process.<n>Our approach achieves state-of-the-art performance, especially for long-term incremental scenarios.
• Score: 25.11059547936733
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Incremental object detection (IOD) aims to cultivate an object detector that can continuously localize and recognize novel classes while preserving its performance on previous classes. Existing methods achieve certain success by improving knowledge distillation and exemplar replay for transformer-based detection frameworks, but the intrinsic forgetting mechanisms remain underexplored. In this paper, we dive into the cause of forgetting and discover forgetting imbalance between localization and recognition in transformer-based IOD, which means that localization is less-forgetting and can generalize to future classes, whereas catastrophic forgetting occurs primarily on recognition. Based on these insights, we propose a Divide-and-Conquer Amnesia (DCA) strategy, which redesigns the transformer-based IOD into a localization-then-recognition process. DCA can well maintain and transfer the localization ability, leaving decoupled fragile recognition to be specially conquered. To reduce feature drift in recognition, we leverage semantic knowledge encoded in pre-trained language models to anchor class representations within a unified feature space across incremental tasks. This involves designing a duplex classifier fusion and embedding class semantic features into the recognition decoding process in the form of queries. Extensive experiments validate that our approach achieves state-of-the-art performance, especially for long-term incremental scenarios. For example, under the four-step setting on MS-COCO, our DCA strategy significantly improves the final AP by 6.9%.

Related papers

• Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector [42.40881712297689]
  Catastrophic forgetting is predominantly localized to the RoI Head.<n>NSGP-RePRE mitigates forgetting via replay of two types of prototypes.<n>NSGP-RePRE achieves state-of-the-art performance on the Pascal VOC and MS COCO datasets.
  arXiv  Detail & Related papers  (2025-02-08T12:10:02Z)
• Exploring Test-Time Adaptation for Object Detection in Continually Changing Environments [13.163784646113214]
  Continual Test-Time Adaptation (CTTA) has recently emerged as a promising technique to gradually adapt a source-trained model to continually changing target domains. We present AMROD, featuring three core components. Firstly, the object-level contrastive learning module extracts object-level features for contrastive learning to refine the feature representation in the target domain. Secondly, the adaptive monitoring module dynamically skips unnecessary adaptation and updates the category-specific threshold based on predicted confidence scores to enable efficiency and improve the quality of pseudo-labels.
  arXiv  Detail & Related papers  (2024-06-24T08:30:03Z)
• Continual-MAE: Adaptive Distribution Masked Autoencoders for Continual Test-Time Adaptation [49.827306773992376]
  Continual Test-Time Adaptation (CTTA) is proposed to migrate a source pre-trained model to continually changing target distributions. Our proposed method attains state-of-the-art performance in both classification and segmentation CTTA tasks.
  arXiv  Detail & Related papers  (2023-12-19T15:34:52Z)
• DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection [37.01880023537362]
  We propose a novel Distillation-based Source Debiasing (DSD) framework for Domain Adaptive Object Detection (DAOD) This framework distills domain-agnostic knowledge from a pre-trained teacher model, improving the detector's performance on both domains. We also present a Domain-aware Consistency Enhancing (DCE) strategy, in which these information are formulated into a new localization representation.
  arXiv  Detail & Related papers  (2023-11-17T10:26:26Z)
• Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning [52.06176253457522]
  We propose a two-stage framework tailored for small object detection based on the Coarse-to-fine pipeline and Feature Imitation learning. CFINet achieves state-of-the-art performance on the large-scale small object detection benchmarks, SODA-D and SODA-A.
  arXiv  Detail & Related papers  (2023-08-18T13:13:09Z)
• CLIP the Gap: A Single Domain Generalization Approach for Object Detection [60.20931827772482]
  Single Domain Generalization tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. We propose to leverage a pre-trained vision-language model to introduce semantic domain concepts via textual prompts. We achieve this via a semantic augmentation strategy acting on the features extracted by the detector backbone, as well as a text-based classification loss.
  arXiv  Detail & Related papers  (2023-01-13T12:01:18Z)
• Localization Distillation for Object Detection [134.12664548771534]
  Previous knowledge distillation (KD) methods for object detection mostly focus on feature imitation instead of mimicking the classification logits. We present a novel localization distillation (LD) method which can efficiently transfer the localization knowledge from the teacher to the student. We show that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit mimicking underperforms for years.
  arXiv  Detail & Related papers  (2022-04-12T17:14:34Z)
• Modulating Localization and Classification for Harmonized Object Detection [40.82723262074911]
  We propose a mutual learning framework to modulate the two tasks. In particular, the two tasks are forced to learn from each other with a novel mutual labeling strategy. We achieve a significant performance gain over the baseline detectors on the COCO dataset.
  arXiv  Detail & Related papers  (2021-03-16T10:36:02Z)
• Scope Head for Accurate Localization in Object Detection [135.9979405835606]
  We propose a novel detector coined as ScopeNet, which models anchors of each location as a mutually dependent relationship. With our concise and effective design, the proposed ScopeNet achieves state-of-the-art results on COCO.
  arXiv  Detail & Related papers  (2020-05-11T04:00:09Z)
• Distilling Knowledge from Refinement in Multiple Instance Detection Networks [0.0]
  Weakly supervised object detection (WSOD) aims to tackle the object detection problem using only labeled image categories as supervision. We present an adaptive supervision aggregation function that dynamically changes the aggregation criteria for selecting boxes related to one of the ground-truth classes, background, or even ignored during the generation of each refinement module supervision.
  arXiv  Detail & Related papers  (2020-04-23T02:49:40Z)
• Incremental Object Detection via Meta-Learning [77.55310507917012]
  We propose a meta-learning approach that learns to reshape model gradients, such that information across incremental tasks is optimally shared. In comparison to existing meta-learning methods, our approach is task-agnostic, allows incremental addition of new-classes and scales to high-capacity models for object detection.
  arXiv  Detail & Related papers  (2020-03-17T13:40:00Z)

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.