Context-Guided Semantic Alignment for Feature Fusion Networks

• URL: http://arxiv.org/abs/2606.14005v1
• Date: Fri, 12 Jun 2026 00:54:11 GMT
• Title: Context-Guided Semantic Alignment for Feature Fusion Networks
• Abstract summary: Feature Interaction NEtwork (FINE) is a lightweight semantic alignment module for feature fusion networks.<n>It refines low-level features via high-level contextual guidance using cross-level attention prior to fusion.<n>It consistently improves detection accuracy without compromising efficiency.
• Score: 9.303501974597548
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Feature fusion networks are fundamental components in modern object detectors, aggregating multi-scale features to detect objects of varying sizes. However, directly fusing features from different pyramid levels often introduces semantic inconsistency due to their heterogeneous representations. In this paper, we propose Feature Interaction NEtwork (FINE), a lightweight semantic alignment module that refines low-level features via high-level contextual guidance using cross-level attention prior to fusion. To bridge the structural gap and ensure computational efficiency, we introduce an Alignment-Aware Token Sampling that aligns corresponding spatial regions across scales, reducing the attention complexity by an order of magnitude. The resulting attention weights generate a spatial-channel modulation map that is upsampled and applied to the low-level features via residual element-wise modulation. This mechanism ensures that the network selectively enhances semantically relevant pixels while preserving the sub-pixel localization accuracy necessary for dense prediction tasks. FINE is generally applicable to various detectors and consistently improves detection accuracy without compromising efficiency.

Related papers

• PICANet: Physics-Informed Cascaded Asymmetric Network for Infrared Small Target Detection [18.422983137700392]
  Infrared small target detection (ISTD) is an important research direction in image processing.<n>Existing methods are limited by severe background noise propagation and target degradation in high-level semantic features.<n>This paper proposes a plug-and-play physics-informed cascaded asymmetric network, named PICANet.
  arXiv  Detail & Related papers  (2026-09-07T14:01:18Z)
• RDNet: Region Proportion-Aware Dynamic Adaptive Salient Object Detection Network in Optical Remote Sensing Images [78.19052099452695]
  We propose the Region Proportion-Aware Dynamic Adaptive Salient Object Detection Network (RDNet)<n>RDNet replaces the CNN backbone with the SwinTransformer for global context modeling.<n>It achieves robustness against scale variations and accurate localization, delivering superior detection performance compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-03-12T17:34:29Z)
• Small Object Detection in Complex Backgrounds with Multi-Scale Attention and Global Relation Modeling [8.24377869183113]
  Small object detection under complex backgrounds is a challenging task due to severe feature degradation, weak semantic representation, and inaccurate localization.<n>Existing detection frameworks are mainly designed for general objects.<n>We propose a multi-level feature enhancement and global relation modeling framework tailored for small object detection.
  arXiv  Detail & Related papers  (2026-03-04T06:57:46Z)
• IoUCert: Robustness Verification for Anchor-based Object Detectors [58.35703549470485]
  We introduce IoUCert, a novel formal verification framework designed specifically to overcome these bottlenecks in anchor-based object detection architectures.<n>We show that our method enables the robustness verification of realistic, anchor-based models including SSD, YOLOv2, and YOLOv3 variants against various input perturbations.
  arXiv  Detail & Related papers  (2026-03-03T14:36:46Z)
• Entropy-Aware Structural Alignment for Zero-Shot Handwritten Chinese Character Recognition [7.632962062462334]
  Zero-shot Handwritten Chinese Character Recognition aims to recognize unseen characters by leveraging radical-based semantic compositions.<n>We propose an Entropy-Aware Structural Alignment Network that bridges the visual-semantic gap through information-theoretic modeling.<n>Our method establishes new state-of-the-art performance, achieving an accuracy of 55.04% on the ICDAR 2013 dataset.
  arXiv  Detail & Related papers  (2026-02-03T16:08:40Z)
• LoFLAT: Local Feature Matching using Focused Linear Attention Transformer [36.53651224633837]
  We propose the LoFLAT, a novel Local Feature matching using Focused Linear Attention Transformer. Our LoFLAT consists of three main modules: the Feature Extraction Module, the Feature Transformer Module, and the Matching Module. The proposed LoFLAT outperforms the LoFTR method in terms of both efficiency and accuracy.
  arXiv  Detail & Related papers  (2024-10-30T05:38:07Z)
• Mesh Denoising Transformer [104.5404564075393]
  Mesh denoising is aimed at removing noise from input meshes while preserving their feature structures. SurfaceFormer is a pioneering Transformer-based mesh denoising framework. New representation known as Local Surface Descriptor captures local geometric intricacies. Denoising Transformer module receives the multimodal information and achieves efficient global feature aggregation.
  arXiv  Detail & Related papers  (2024-05-10T15:27:43Z)
• Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion [62.269219152425556]
  segmentation-based scene text detection methods have drawn extensive attention in the scene text detection field. We propose a Differentiable Binarization (DB) module that integrates the binarization process into a segmentation network. An efficient Adaptive Scale Fusion (ASF) module is proposed to improve the scale robustness by fusing features of different scales adaptively.
  arXiv  Detail & Related papers  (2022-02-21T15:30:14Z)
• Adaptive Linear Span Network for Object Skeleton Detection [56.78705071830965]
  We propose adaptive linear span network (AdaLSN) to automatically configure and integrate scale-aware features for object skeleton detection. AdaLSN substantiates its versatility by achieving significantly higher accuracy and latency trade-off. It also demonstrates general applicability to image-to-mask tasks such as edge detection and road extraction.
  arXiv  Detail & Related papers  (2020-11-08T12:51:14Z)
• Align Deep Features for Oriented Object Detection [40.28244152216309]
  We propose a single-shot Alignment Network (S$2$A-Net) consisting of two modules: a Feature Alignment Module (FAM) and an Oriented Detection Module (ODM) The FAM can generate high-quality anchors with an Anchor Refinement Network and adaptively align the convolutional features according to the anchor boxes with a novel Alignment Convolution. The ODM first adopts active rotating filters to encode the orientation information and then produces orientation-sensitive and orientation-invariant features to alleviate the inconsistency between classification score and localization accuracy.
  arXiv  Detail & Related papers  (2020-08-21T09:55:13Z)
• Cross-layer Feature Pyramid Network for Salient Object Detection [102.20031050972429]
  We propose a novel Cross-layer Feature Pyramid Network to improve the progressive fusion in salient object detection. The distributed features per layer own both semantics and salient details from all other layers simultaneously, and suffer reduced loss of important information.
  arXiv  Detail & Related papers  (2020-02-25T14:06:27Z)

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.