SDDF: Specificity-Driven Dynamic Focusing for Open-Vocabulary Camouflaged Object Detection

• URL: http://arxiv.org/abs/2603.26109v1
• Date: Fri, 27 Mar 2026 06:37:32 GMT
• Title: SDDF: Specificity-Driven Dynamic Focusing for Open-Vocabulary Camouflaged Object Detection
• Abstract summary: Open-vocabulary object detection (OVOD) aims to detect known and unknown objects in the open world by leveraging text prompts.<n>We construct a benchmark named OVCOD-D by augmenting carefully selected camouflaged object images with fine-grained textual descriptions.<n>Under the open-set evaluation setting, the proposed method achieves an AP of 56.4 on the OVCOD-D benchmark.
• Score: 12.404050551208366
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Open-vocabulary object detection (OVOD) aims to detect known and unknown objects in the open world by leveraging text prompts. Benefiting from the emergence of large-scale vision--language pre-trained models, OVOD has demonstrated strong zero-shot generalization capabilities. However, when dealing with camouflaged objects, the detector often fails to distinguish and localize objects because the visual features of the objects and the background are highly similar. To bridge this gap, we construct a benchmark named OVCOD-D by augmenting carefully selected camouflaged object images with fine-grained textual descriptions. Due to the limited scale of available camouflaged object datasets, we adopt detectors pre-trained on large-scale object detection datasets as our baseline methods, as they possess stronger zero-shot generalization ability. In the specificity-aware sub-descriptions generated by multimodal large models, there still exist confusing and overly decorative modifiers. To mitigate such interference, we design a sub-description principal component contrastive fusion strategy that reduces noisy textual components. Furthermore, to address the challenge that the visual features of camouflaged objects are highly similar to those of their surrounding environment, we propose a specificity-guided regional weak alignment and dynamic focusing method, which aims to strengthen the detector's ability to discriminate camouflaged objects from background. Under the open-set evaluation setting, the proposed method achieves an AP of 56.4 on the OVCOD-D benchmark.

Related papers

• ECAD: Expanding Class-Agnostic Detection Beyond Thing-Centric Objectness [19.94019125942239]
  We formulate Expanded Class-Agnostic Detection (ECAD), a new setting that aims to discover category-agnostic visual candidates.<n>ECADet is a lightweight DETR-based detector built upon a frozen DINOv3 encoder.<n>We show that ECADet consistently outperforms representative class-agnostic and proposal-based detectors on BTCO-Bench.
  arXiv  Detail & Related papers  (2026-08-07T06:01:06Z)
• LOGOS: Language-guided Oriented Object Detection in Aerial Scenes [13.035539845858501]
  In this paper, we propose LOGOS, a novel transformer-based approach that leverages textual prompts to guide the detection of oriented objects in aerial scenes.<n>In particular, our proposed approach incorporates prompt-modulated content queries to dynamically adjust the model's focus based on the provided text.<n>Our approach offers a significant step forward in improving the robustness and scalability of oriented object detection in remote sensing applications.
  arXiv  Detail & Related papers  (2026-07-09T00:11:48Z)
• CAMotion: A High-Quality Benchmark for Camouflaged Moving Object Detection in the Wild [83.45543969516149]
  In this paper, we construct CAMotion, a high-quality benchmark for camouflaged moving object detection in the wild.<n>The benchmark provides in-depth analyses on the camouflaged object's motion characteristics in different challenging scenarios.<n>We also conduct a comprehensive evaluation of existing SOTA models on CAMotion, and discuss the major challenges in VCOD task.
  arXiv  Detail & Related papers  (2026-04-09T14:23:46Z)
• Toward Realistic Camouflaged Object Detection: Benchmarks and Method [11.279532701331647]
  Camouflaged object detection (COD) primarily relies on semantic or instance segmentation methods.<n>We propose a camouflage-aware feature refinement (CAFR) strategy to detect camouflaged objects.<n>CAFR fully utilizes a clear perception of the current object within the prior knowledge of large models to assist detectors in deeply understanding the distinctions between background and foreground.
  arXiv  Detail & Related papers  (2025-01-13T13:04:00Z)
• UN-DETR: Promoting Objectness Learning via Joint Supervision for Unknown Object Detection [6.837147490662261]
  Unknown Object Detection (UOD) aims to identify objects of unseen categories, differing from the traditional detection paradigm limited by the closed-world assumption.<n>Previous methods obtain supervision signals for learning objectness in isolation from either localization or classification information, leading to poor performance for UOD.<n>We propose a transformer-based UOD framework, UN-DETR. Based on this, we craft Instance Presence Score (IPS) to represent the probability of an object's presence.
  arXiv  Detail & Related papers  (2024-12-13T14:45:11Z)
• OW-Rep: Open World Object Detection with Instance Representation Learning [1.8749305679160366]
  Open World Object Detection (OWOD) addresses realistic scenarios where unseen object classes emerge.<n>We extend the OWOD framework to jointly detect unknown objects and learn semantically rich instance embeddings.
  arXiv  Detail & Related papers  (2024-09-24T13:13:34Z)
• Learning Background Prompts to Discover Implicit Knowledge for Open Vocabulary Object Detection [101.15777242546649]
  Open vocabulary object detection (OVD) aims at seeking an optimal object detector capable of recognizing objects from both base and novel categories. Recent advances leverage knowledge distillation to transfer insightful knowledge from pre-trained large-scale vision-language models to the task of object detection. We present a novel OVD framework termed LBP to propose learning background prompts to harness explored implicit background knowledge.
  arXiv  Detail & Related papers  (2024-06-01T17:32:26Z)
• Detecting Every Object from Events [24.58024539462497]
  We propose Detecting Every Object in Events (DEOE), an approach tailored for achieving high-speed, class-agnostic open-world object detection in event-based vision. Our code is available at https://github.com/Hatins/DEOE.
  arXiv  Detail & Related papers  (2024-04-08T08:20:53Z)
• Frequency Perception Network for Camouflaged Object Detection [51.26386921922031]
  We propose a novel learnable and separable frequency perception mechanism driven by the semantic hierarchy in the frequency domain.<n>Our entire network adopts a two-stage model, including a frequency-guided coarse localization stage and a detail-preserving fine localization stage.<n>Compared with the currently existing models, our proposed method achieves competitive performance in three popular benchmark datasets.
  arXiv  Detail & Related papers  (2023-08-17T11:30:46Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• High-resolution Iterative Feedback Network for Camouflaged Object Detection [128.893782016078]
  Spotting camouflaged objects that are visually assimilated into the background is tricky for object detection algorithms. We aim to extract the high-resolution texture details to avoid the detail degradation that causes blurred vision in edges and boundaries. We introduce a novel HitNet to refine the low-resolution representations by high-resolution features in an iterative feedback manner.
  arXiv  Detail & Related papers  (2022-03-22T11:20:21Z)
• Scribble-based Boundary-aware Network for Weakly Supervised Salient Object Detection in Remote Sensing Images [10.628932392896374]
  We propose a novel weakly-supervised salient object detection framework to predict the saliency of remote sensing images from sparse scribble annotations. Specifically, we design a boundary-aware module (BAM) to explore the object boundary semantics, which is explicitly supervised by the high-confidence object boundary (pseudo) labels. Then, the boundary semantics are integrated with high-level features to guide the salient object detection under the supervision of scribble labels.
  arXiv  Detail & Related papers  (2022-02-07T20:32:21Z)
• Slender Object Detection: Diagnoses and Improvements [74.40792217534]
  In this paper, we are concerned with the detection of a particular type of objects with extreme aspect ratios, namely textbfslender objects. For a classical object detection method, a drastic drop of $18.9%$ mAP on COCO is observed, if solely evaluated on slender objects.
  arXiv  Detail & Related papers  (2020-11-17T09:39:42Z)

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.