FOAM: A General Frequency-Optimized Anti-Overlapping Framework for Overlapping Object Perception

2025-06-16

AI Summary

Overlapping objects cause severe degradation in object contours and textures, leading existing methods—largely confined to spatial-domain modeling—to struggle with disentangling foreground from background features. Method: We propose a frequency-spatial collaborative anti-overlap perception framework. First, we observe that overlap-induced degradation exhibits high discriminability in the amplitude spectrum. Building on this, we design a novel Frequency-Spatial Transformer Block (FSTB) for dual-domain joint modeling and introduce a Hierarchical Decontamination Mechanism (HDC) that suppresses background responses via alignment between clean and contaminated feature branches. Our method integrates FFT-based spectral analysis, frequency-spatial Transformers, dual-branch contrastive learning, and multi-task consistency loss. Contribution/Results: The framework achieves significant improvements over state-of-the-art methods across four benchmark datasets, notably enhancing foreground contour perception accuracy in three challenging overlapping scenarios: prohibited-item detection/segmentation and pneumonia identification.

Technology Category

• Computer Vision: Segmentation
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Overlapping object perception aims to decouple the randomly overlapping foreground-background features, extracting foreground features while suppressing background features, which holds significant application value in fields such as security screening and medical auxiliary diagnosis. Despite some research efforts to tackle the challenge of overlapping object perception, most solutions are confined to the spatial domain. Through frequency domain analysis, we observe that the degradation of contours and textures due to the overlapping phenomenon can be intuitively reflected in the magnitude spectrum. Based on this observation, we propose a general Frequency-Optimized Anti-Overlapping Framework (FOAM) to assist the model in extracting more texture and contour information, thereby enhancing the ability for anti-overlapping object perception. Specifically, we design the Frequency Spatial Transformer Block (FSTB), which can simultaneously extract features from both the frequency and spatial domains, helping the network capture more texture features from the foreground. In addition, we introduce the Hierarchical De-Corrupting (HDC) mechanism, which aligns adjacent features in the separately constructed base branch and corruption branch using a specially designed consistent loss during the training phase. This mechanism suppresses the response to irrelevant background features of FSTBs, thereby improving the perception of foreground contour. We conduct extensive experiments to validate the effectiveness and generalization of the proposed FOAM, which further improves the accuracy of state-of-the-art models on four datasets, specifically for the three overlapping object perception tasks: Prohibited Item Detection, Prohibited Item Segmentation, and Pneumonia Detection. The code will be open source once the paper is accepted.

Problem

• Decoupling overlapping foreground-background features in object perception
• Enhancing texture and contour extraction via frequency domain optimization
• Improving accuracy in overlapping object perception tasks

Innovation

• Frequency-Optimized Anti-Overlapping Framework (FOAM)
• Frequency Spatial Transformer Block (FSTB)
• Hierarchical De-Corrupting (HDC) mechanism