CFCamo: A Counterfactual Detect-or-Abstain Framework for Camouflaged Object Detection

• URL: http://arxiv.org/abs/2606.11231v1
• Date: Thu, 28 May 2026 20:14:17 GMT
• Title: CFCamo: A Counterfactual Detect-or-Abstain Framework for Camouflaged Object Detection
• Abstract summary: Vision-language reinforcement learning has recently shown strong target-present localization for camouflaged object detection (COD)<n>Standard COD training and evaluation data are positive-only, so agents optimized under this setting can acquire an over-detect bias.<n>To quantify this target-absent behavior, we construct Counterfactual COD (CF-COD), a paired benchmark that removes the camouflaged target from each held-out COD evaluation image.
• Score: 3.995408039775796
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language reinforcement learning has recently shown strong target-present localization for camouflaged object detection (COD). Yet localization is only one side of the decision: when the agent faces an ordinary image with no camouflaged target, will it still claim that a camouflaged object exists? Standard COD training and evaluation data are positive-only, so agents optimized under this setting can acquire an over-detect bias, a task-specific form of object hallucination that standard COD evaluation leaves unmeasured. To quantify this target-absent behavior, we construct Counterfactual COD (CF-COD), a paired benchmark that removes the camouflaged target from each held-out COD evaluation image while preserving a plausible background. CF-COD evaluates whether a model detects the target on the original image and abstains on the target-absent counterfactual, summarized by Pair Accuracy (PA). We further introduce CFCamo, a paired counterfactual framework for COD with abstention. For training, CFCamo optimizes a Qwen3-VL-4B-Instruct agent with Counterfactual Sequence Policy Optimization (CSPO), which samples paired original-counterfactual rollouts and uses a Counterfactual Paired Reward (CPR) to couple original-image detection with counterfactual abstention. On CAMO-test, CFCamo improves S_alpha by +3.7 pp over the prior RL-based COD baseline; across CF-COD, it reaches 80.0-90.8% PA. Ablations show that removing counterfactual coupling reduces PA to 1.4-5.2% despite strong target-present COD scores, showing that target-present evaluation alone does not characterize detect-or-abstain behavior. Overall, these results indicate that CFCamo improves COD agents by coupling target-present detection with target-absent abstention, rather than merely strengthening target-present localization. Code and data are available at https://github.com/suhang2000/CFCamo.

Related papers

• Is There Really a Camouflaged Object? Towards Realistic Camouflaged Object Detection [34.38693223357721]
  Camouflaged object detection (COD) aims to segment objects that are visually concealed in their surroundings.<n>Most existing COD methods are developed under a closed-world assumption, where each input image is assumed to contain a camouflaged object.<n>This assumption ignores realistic scenarios with pure backgrounds or non-camouflaged objects, causing existing models to produce severe false positives when deployed in open-world environments.
  arXiv  Detail & Related papers  (2026-08-11T16:57:40Z)
• LeakBoost: Perceptual-Loss-Based Membership Inference Attack [4.82560917771631]
  LeakBoost is a perceptual-loss-based interrogation framework that actively probes a model's internal representations to expose hidden membership signals.<n>LeakBoost achieves substantial improvements at low false-positive rates across multiple image classification datasets and diverse neural network architectures.
  arXiv  Detail & Related papers  (2026-02-05T15:15:35Z)
• Uncertainty Quantification for Collaborative Object Detection Under Adversarial Attacks [6.535251134834875]
  Collaborative Object Detection (COD) and collaborative perception can integrate data or features from various entities.<n> adversarial attacks pose a potential threat to the deep learning COD models.<n>We propose the Trusted Uncertainty Quantification in Collaborative Perception framework (TUQCP)
  arXiv  Detail & Related papers  (2025-02-04T18:03:32Z)
• Seamless Detection: Unifying Salient Object Detection and Camouflaged Object Detection [73.85890512959861]
  We propose a task-agnostic framework to unify Salient Object Detection (SOD) and Camouflaged Object Detection (COD)<n>We design a simple yet effective contextual decoder involving the interval-layer and global context, which achieves an inference speed of 67 fps.<n> Experiments on public SOD and COD datasets demonstrate the superiority of our proposed framework in both supervised and unsupervised settings.
  arXiv  Detail & Related papers  (2024-12-22T03:25:43Z)
• Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes [5.876510569597584]
  We propose a model called USCNet to explicitly model the relationship between salient and camouflaged objects.<n>To assess the model's ability to distinguish between salient and camouflaged objects, we design an evaluation metric called CSCS.
  arXiv  Detail & Related papers  (2024-12-14T19:37:17Z)
• From COCO to COCO-FP: A Deep Dive into Background False Positives for COCO Detectors [8.3561487803637]
  False alarms in fire and smoke detection are critical in real-world applications. COCO-FP is a new evaluation dataset derived from the ImageNet-1K dataset. Our evaluation of both standard and advanced object detectors shows a significant number of false positives in both closed-set and open-set scenarios.
  arXiv  Detail & Related papers  (2024-09-12T10:22:12Z)
• SAM-COD: SAM-guided Unified Framework for Weakly-Supervised Camouflaged Object Detection [12.915303163650002]
  Most Camouflaged Object Detection (COD) methods heavily rely on mask annotations, which are time-consuming and labor-intensive to acquire. Existing weakly-supervised COD approaches exhibit significantly inferior performance compared to fully-supervised methods. We propose a unified COD framework, termed SAM-COD, which is capable of supporting arbitrary weakly-supervised labels.
  arXiv  Detail & Related papers  (2024-08-20T11:49:27Z)
• AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning [93.77763753231338]
  Adversarial Contrastive Prompt Tuning (ACPT) is proposed to fine-tune the CLIP image encoder to extract similar embeddings for any two intermediate adversarial queries. We show that ACPT can detect 7 state-of-the-art query-based attacks with $>99%$ detection rate within 5 shots. We also show that ACPT is robust to 3 types of adaptive attacks.
  arXiv  Detail & Related papers  (2024-08-04T09:53:50Z)
• Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects [107.47530456103758]
  Camouflaged object detection (COD) is the challenging task of identifying camouflaged objects visually blended into surroundings. We draw inspiration from the prey-vs-predator game that leads preys to develop better camouflage and predators to acquire more acute vision systems. We introduce a novel COD method, called Internal Coherence and Edge Guidance (ICEG), which introduces a camouflaged feature coherence module.
  arXiv  Detail & Related papers  (2023-08-06T17:27:08Z)
• CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models [72.93652777646233]
  Camouflaged Object Detection (COD) is a challenging task in computer vision due to the high similarity between camouflaged objects and their surroundings. We propose a new paradigm that treats COD as a conditional mask-generation task leveraging diffusion models. Our method, dubbed CamoDiffusion, employs the denoising process of diffusion models to iteratively reduce the noise of the mask.
  arXiv  Detail & Related papers  (2023-05-29T07:49:44Z)
• CamDiff: Camouflage Image Augmentation via Diffusion Model [83.35960536063857]
  CamDiff is a novel approach to synthesize salient objects in camouflaged scenes. We leverage the latent diffusion model to synthesize salient objects in camouflaged scenes. Our approach enables flexible editing and efficient large-scale dataset generation at a low cost.
  arXiv  Detail & Related papers  (2023-04-11T19:37:47Z)
• Object-fabrication Targeted Attack for Object Detection [54.10697546734503]
  adversarial attack for object detection contains targeted attack and untargeted attack. New object-fabrication targeted attack mode can mislead detectors tofabricate extra false objects with specific target labels.
  arXiv  Detail & Related papers  (2022-12-13T08:42:39Z)

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.