COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection

• URL: http://arxiv.org/abs/2605.27116v1
• Date: Tue, 26 May 2026 14:53:14 GMT
• Title: COVD: Continual Open-Vocabulary Object Detection with Novel Concept Injection
• Abstract summary: We introduce a new task setting, termed Continual OVD with Novel Concept Injection (COVD), where models sequentially learn incoming novel concept groups.<n>Our key observation is that pretrained visual encoders often already perceive and represent many novel concepts.<n>We propose NoIn-Det, an efficient continual injection framework without additional parameters.
• Score: 24.164864713386446
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open-vocabulary object detection (OVD) has made significant progress, enabling detectors to generalize from seen to unseen categories. However, real-world category spaces continually evolve, and existing OVD models still struggle with newly emerging concepts, while repeated full retraining is prohibitively expensive. To this end, we introduce a new task setting, termed Continual OVD with Novel Concept Injection (COVD), where models sequentially learn incoming novel concept groups while preserving prior concepts and original open-vocabulary knowledge, along with a new benchmark, Novel-114. Our key observation is that pretrained visual encoders often already perceive and represent many novel concepts, and the main bottleneck lies in the lack of stable semantic alignment between visual representations and textual concepts. Based on this, we propose NoIn-Det, an efficient continual injection framework without additional parameters. NoIn-Det freezes the visual encoder, preserves the text representation space using only texts of common concepts and previously injected concepts, and injects novel concepts by updating only a small subset of text-branch parameters beneficial to novel concept learning. Extensive experiments show that NoIn-Det effectively learns novel concepts, preserves old knowledge, and consistently outperforms existing continual learning methods for VLMs without introducing additional parameters.Novel-114 and the code will be released.

Related papers

• Uni-AdaVD: Universal Concept Erasure for Visual Generation via Orthogonal Value Decomposition [62.947473058878565]
  We present Uni-AdaVD, a universal inference-time concept erasure framework for visual generation.<n>Our results suggest that Uni-AdaVD provides an efficient and adaptable safety mechanism for modern visual generative models.
  arXiv  Detail & Related papers  (2026-07-16T03:16:51Z)
• LINE: LLM-based Iterative Neuron Explanations for Vision Models [0.0]
  We introduce LINE, a training-free iterative approach tailored for open-vocabulary concept labeling in vision models.<n> LINE achieves state-of-the-art performance across multiple model architectures, yielding AUC improvements of up to 0.18 on ImageNet and 0.05 on Places365.<n> LINE provides a complete generation history, which enables polysemanticity evaluation and produces visual explanations that rival gradient-dependent activation methods.
  arXiv  Detail & Related papers  (2026-04-09T09:43:26Z)
• TINA: Text-Free Inversion Attack for Unlearned Text-to-Image Diffusion Models [92.56562999211809]
  A text-centric paradigm equates erasure with severing the text-to-image mapping, ignoring that the underlying visual knowledge related to undesired concepts still persist.<n>We introduce Tina, a novel Text-free INversion Attack, which enforces this visual-only probe by operating under a null-text condition.<n>Our experiments demonstrate that Tina regenerates erased concepts from models treated with state-of-the-art unlearning.
  arXiv  Detail & Related papers  (2026-03-18T15:25:03Z)
• Bring Your Dreams to Life: Continual Text-to-Video Customization [76.70414091514704]
  We develop a novel Continual Customized Video Diffusion model to tackle forgetting and concept neglect.<n>To tackle concept neglect, we develop a controllable conditional synthesis to enhance regional features and align video contexts with user conditions.<n>Our CCVD outperforms existing CTVG baselines on both the DreamVideo and Wan 2.1 backbones.
  arXiv  Detail & Related papers  (2025-12-05T15:25:56Z)
• FaCT: Faithful Concept Traces for Explaining Neural Network Decisions [56.796533084868884]
  Deep networks have shown remarkable performance across a wide range of tasks, yet getting a global concept-level understanding of how they function remains a key challenge.<n>We put emphasis on the faithfulness of concept-based explanations and propose a new model with model-inherent mechanistic concept-explanations.<n>Our concepts are shared across classes and, from any layer, their contribution to the logit and their input-visualization can be faithfully traced.
  arXiv  Detail & Related papers  (2025-10-29T13:35:46Z)
• Scaling Concept With Text-Guided Diffusion Models [53.80799139331966]
  Instead of replacing a concept, can we enhance or suppress the concept itself? We introduce ScalingConcept, a simple yet effective method to scale decomposed concepts up or down in real input without introducing new elements. More importantly, ScalingConcept enables a variety of novel zero-shot applications across image and audio domains.
  arXiv  Detail & Related papers  (2024-10-31T17:09:55Z)
• How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization? [91.49559116493414]
  We propose a novel Concept-Incremental text-to-image Diffusion Model (CIDM) It can resolve catastrophic forgetting and concept neglect to learn new customization tasks in a concept-incremental manner. Experiments validate that our CIDM surpasses existing custom diffusion models.
  arXiv  Detail & Related papers  (2024-10-23T06:47:29Z)
• Conceptual Codebook Learning for Vision-Language Models [27.68834532978939]
  We propose Codebook Learning (CoCoLe) to address the challenge of improving the generalization capability of vision-language models (VLMs) We learn a conceptual codebook consisting of visual concepts as keys and conceptual prompts as values. We observe that this conceptual codebook learning method is able to achieve enhanced alignment between visual and linguistic modalities.
  arXiv  Detail & Related papers  (2024-07-02T15:16:06Z)
• Neural Concept Binder [22.074896812195437]
  We introduce the Neural Concept Binder (NCB), a framework for deriving both discrete and continuous concept representations. The structured nature of NCB's concept representations allows for intuitive inspection and the straightforward integration of external knowledge. We validate the effectiveness of NCB through evaluations on our newly introduced CLEVR-Sudoku dataset.
  arXiv  Detail & Related papers  (2024-06-14T11:52:09Z)
• Coarse-to-Fine Concept Bottleneck Models [9.910980079138206]
  This work targets ante hoc interpretability, and specifically Concept Bottleneck Models (CBMs) Our goal is to design a framework that admits a highly interpretable decision making process with respect to human understandable concepts, on two levels of granularity. Within this framework, concept information does not solely rely on the similarity between the whole image and general unstructured concepts; instead, we introduce the notion of concept hierarchy to uncover and exploit more granular concept information residing in patch-specific regions of the image scene.
  arXiv  Detail & Related papers  (2023-10-03T14:57:31Z)

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.