Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection

• URL: http://arxiv.org/abs/2407.20078v3
• Date: Tue, 07 Oct 2025 09:53:45 GMT
• Title: Background Semantics Matter: Cross-Task Feature Exchange Network for Clustered Infrared Small Target Detection
• Authors: Mengxuan Xiao, Yinfei Zhu, Yiming Zhu, Boyang Li, Feifei Zhang, Huan Wang, Meng Cai, Yimian Dai,
• Abstract summary: Infrared small target detection presents significant challenges due to the limited intrinsic features of the target.<n>Background semantics are critical for distinguishing between objects that appear visually similar in this context.<n>DenseSIRST is a benchmark dataset that provides per-pixel semantic annotations for background regions.<n>BAFE-Net is a multi-task architecture that jointly tackles target detection and background semantic segmentation.
• Score: 22.796713788625294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Infrared small target detection presents significant challenges due to the limited intrinsic features of the target and the overwhelming presence of visually similar background distractors. We contend that background semantics are critical for distinguishing between objects that appear visually similar in this context. To address this challenge, we propose a task, clustered infrared small target detection, and introduce DenseSIRST, a benchmark dataset that provides per-pixel semantic annotations for background regions. This dataset facilitates the shift from sparse to dense target detection. This dataset facilitates the shift from sparse to dense target detection. Building on this resource, we propose the Background-Aware Feature Exchange Network (BAFE-Net), a multi-task architecture that jointly tackles target detection and background semantic segmentation. BAFE-Net incorporates a dynamic cross-task feature hard-exchange mechanism, enabling the effective exchange of target and background semantics between the two tasks. Comprehensive experiments demonstrate that BAFE-Net significantly enhances target detection accuracy while mitigating false alarms. The DenseSIRST dataset, along with the code and trained models, is publicly available at https://github.com/GrokCV/BAFE-Net.

Related papers

• DCCS-Det: Directional Context and Cross-Scale-Aware Detector for Infrared Small Target [4.318503966844226]
  Infrared small target detection (IRSTD) is critical for applications like remote sensing and surveillance.<n>We propose DCCS-Det, a novel detector that incorporates a Dual-stream Saliency Enhancement (DSE) block and a Latent-aware Semantic Extraction and Aggregation (LaSEA) module.<n>Experiments show that DCCS-Det achieves state-of-the-art detection accuracy with competitive efficiency across multiple datasets.
  arXiv  Detail & Related papers  (2026-01-23T03:53:59Z)
• It's Not the Target, It's the Background: Rethinking Infrared Small Target Detection via Deep Patch-Free Low-Rank Representations [5.326302374594885]
  In this paper, we propose a novel end-to-end IRSTD framework, termed LRRNet.<n>Inspired by the physical compressibility of cluttered scenes, our approach adopts a compression-reconstruction-subtraction paradigm.<n>Experiments on multiple public datasets demonstrate that LRRNet outperforms 38 state-of-the-art methods in terms of detection accuracy, robustness, and computational efficiency.
  arXiv  Detail & Related papers  (2025-06-12T07:24:45Z)
• Toward Realistic Camouflaged Object Detection: Benchmarks and Method [11.279532701331647]
  Camouflaged object detection (COD) primarily relies on semantic or instance segmentation methods. We propose a camouflage-aware feature refinement (CAFR) strategy to detect camouflaged objects. 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)
• LAC-Net: Linear-Fusion Attention-Guided Convolutional Network for Accurate Robotic Grasping Under the Occlusion [79.22197702626542]
  This paper introduces a framework that explores amodal segmentation for robotic grasping in cluttered scenes. We propose a Linear-fusion Attention-guided Convolutional Network (LAC-Net) The results on different datasets show that our method achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-08-06T14:50:48Z)
• Sparse Prior Is Not All You Need: When Differential Directionality Meets Saliency Coherence for Infrared Small Target Detection [15.605122893098981]
  This study introduces a Sparse Differential Directionality prior (SDD) framework. We leverage the distinct directional characteristics of targets to differentiate them from the background. We further enhance target detectability with a saliency coherence strategy. A Proximal Alternating Minimization-based (PAM) algorithm efficiently solves our proposed model.
  arXiv  Detail & Related papers  (2024-07-22T04:32:43Z)
• FIPGNet:Pyramid grafting network with feature interaction strategies [0.0]
  We propose a new salience object detection framework(FIPGNet), which is a pyramid graft network with feature interaction strategies. Specifically, we propose an attention-mechanism based feature interaction strategy (FIA) that innovatively introduces spatial agent Cross Attention. The proposed method outperforms the current 12 salient object detection methods on four indicators.
  arXiv  Detail & Related papers  (2024-07-04T17:53:37Z)
• Better Sampling, towards Better End-to-end Small Object Detection [7.7473020808686694]
  Small object detection remains unsatisfactory due to limited characteristics and high density and mutual overlap. We propose methods enhancing sampling within an end-to-end framework. Our model demonstrates a significant enhancement, achieving a 2.9% increase in average precision (AP) over the state-of-the-art (SOTA) on the VisDrone dataset.
  arXiv  Detail & Related papers  (2024-05-17T04:37:44Z)
• Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection [55.2480439325792]
  We present an in-depth evaluation of an object detection model that integrates the LSKNet backbone with the DiffusionDet head. The proposed model achieves a mean average precision (MAP) of approximately 45.7%, which is a significant improvement. This advancement underscores the effectiveness of the proposed modifications and sets a new benchmark in aerial image analysis.
  arXiv  Detail & Related papers  (2023-11-21T19:49:13Z)
• EFLNet: Enhancing Feature Learning for Infrared Small Target Detection [20.546186772828555]
  Single-frame infrared small target detection is considered to be a challenging task. Due to the extreme imbalance between target and background, bounding box regression is extremely sensitive to infrared small target. We propose an enhancing feature learning network (EFLNet) to address these problems.
  arXiv  Detail & Related papers  (2023-07-27T09:23:22Z)
• Label-Efficient Object Detection via Region Proposal Network Pre-Training [58.50615557874024]
  We propose a simple pretext task that provides an effective pre-training for the region proposal network (RPN) In comparison with multi-stage detectors without RPN pre-training, our approach is able to consistently improve downstream task performance.
  arXiv  Detail & Related papers  (2022-11-16T16:28:18Z)
• A Multi-task Framework for Infrared Small Target Detection and Segmentation [9.033048310220346]
  We propose a novel end-to-end framework for infrared small target detection and segmentation. We use UNet as the backbone to maintain resolution and semantic information. We develop a multi-task framework for infrared small target detection and segmentation.
  arXiv  Detail & Related papers  (2022-06-14T15:43:34Z)
• Context-Preserving Instance-Level Augmentation and Deformable Convolution Networks for SAR Ship Detection [50.53262868498824]
  Shape deformation of targets in SAR image due to random orientation and partial information loss is an essential challenge in SAR ship detection. We propose a data augmentation method to train a deep network that is robust to partial information loss within the targets.
  arXiv  Detail & Related papers  (2022-02-14T07:01:01Z)
• Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network [17.538512222905087]
  This paper proposes a novel edge-based reversible re-calibration network called ERRNet. Our model is characterized by two innovative designs, namely Selective Edge Aggregation (SEA) and Reversible Re-calibration Unit (RRU) Experimental results show that ERRNet outperforms existing cutting-edge baselines on three COD datasets and five medical image segmentation datasets.
  arXiv  Detail & Related papers  (2021-11-05T02:03:54Z)
• Infrared Small-Dim Target Detection with Transformer under Complex Backgrounds [155.388487263872]
  We propose a new infrared small-dim target detection method with the transformer. We adopt the self-attention mechanism of the transformer to learn the interaction information of image features in a larger range. We also design a feature enhancement module to learn more features of small-dim targets.
  arXiv  Detail & Related papers  (2021-09-29T12:23:41Z)
• Location-Sensitive Visual Recognition with Cross-IOU Loss [177.86369890708457]
  This paper proposes a unified solution named location-sensitive network (LSNet) for object detection, instance segmentation, and pose estimation. Based on a deep neural network as the backbone, LSNet predicts an anchor point and a set of landmarks which together define the shape of the target object.
  arXiv  Detail & Related papers  (2021-04-11T02:17:14Z)
• Uncertainty-aware Joint Salient Object and Camouflaged Object Detection [43.01556978979627]
  We propose a paradigm of leveraging the contradictory information to enhance the detection ability of both salient object detection and camouflaged object detection. We introduce a similarity measure module to explicitly model the contradicting attributes of these two tasks. Considering the uncertainty of labeling in both tasks' datasets, we propose an adversarial learning network to achieve both higher order similarity measure and network confidence estimation.
  arXiv  Detail & Related papers  (2021-04-06T16:05:10Z)
• FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking [92.48078680697311]
  Multi-object tracking (MOT) is an important problem in computer vision. We present a simple yet effective approach termed as FairMOT based on the anchor-free object detection architecture CenterNet. The approach achieves high accuracy for both detection and tracking.
  arXiv  Detail & Related papers  (2020-04-04T08:18:00Z)
• Depthwise Non-local Module for Fast Salient Object Detection Using a Single Thread [136.2224792151324]
  We propose a new deep learning algorithm for fast salient object detection. The proposed algorithm achieves competitive accuracy and high inference efficiency simultaneously with a single CPU thread.
  arXiv  Detail & Related papers  (2020-01-22T15:23:48Z)
• TBC-Net: A real-time detector for infrared small target detection using semantic constraint [18.24737906712967]
  Deep learning is rarely used in infrared small target detection due to the difficulty in learning small target features. We propose a novel lightweight convolutional neural network TBC-Net for infrared small target detection.
  arXiv  Detail & Related papers  (2019-12-27T05:25:39Z)

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.