Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection

• URL: http://arxiv.org/abs/2606.26849v1
• Date: Thu, 25 Jun 2026 10:35:42 GMT
• Title: Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection
• Abstract summary: General Salient Object Detection (SOD) aims to identify and segment visually interesting objects from uni-modality or multi-modality scenes.<n>We introduce a liquid fusion to dynamically integrate features from two backbones, including VMamba and ConvNeXt, referred to Liquid Fusion Network (LFNet)<n>LFNet achieves state-of-the-art performance, offering a superior trade-off between detection accuracy and model efficiency.
• Score: 17.9670241907852
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: General Salient Object Detection (SOD) aims to identify and segment visually interesting objects from uni-modality or multi-modality scenes, recently advanced by cutting-edge State Space Models (SSMs). However, a critical limitation of current approaches is their neglect of the inherent spectral biases exhibited by different neural network paradigms. By digging to the dataset-level spectral analysis of Convolutional Neural Networks (CNNs) and SSMs, their semantic representations are inherently complementary based on their complementary frequency preferences. Inspired by this, we harmonize heterogeneous representations from SSMs and CNNs to bridge their spectral biases for general salient object detection. To this end, inspired by the dynamic information propagation of Liquid Neural Networks (LNNs), we introduce a liquid fusion to dynamically integrates features from two backbones, including VMamba and ConvNeXt, referred to Liquid Fusion Network (LFNet). Concretely, by treating the continuous VMamba features and ConvNeXt features as evolving states and exogenous stimulus, respectively, LFNet employs a dynamic gating mechanism for content-aware feature aggregation. Crucially, this state-stimulus paradigm enables to scale to multi-modal cues, resulting in flexibility in general SOD. Besides, a Saliency-Guided Upsampling (SGU) operator to propagate the features to the shallow layer, which leverages a spectral-spatial co-design to suppress upsampling artifacts while preserving semantics. Extensive experiments across five diverse tasks (RGB, RGB-D, RGB-T, VSOD, and VDT) demonstrate that LFNet achieves state-of-the-art performance, offering a superior trade-off between detection accuracy and model efficiency. Code has been released at https://github.com/cke520/LFNet.

Related papers

• MSP-Net: Manifold-Guided Spectral Prompt Network for Hyperspectral Object Tracking [11.03462046191901]
  Hyperspectral object tracking offers unique advantages for target discrimination in complex scenes.<n>Existing methods treat hyperspectral images as multi-channel extensions of RGB images, performing feature fusion in fixed band order.<n>We propose the Manifold-Guided Spectral Prompt Network (MSP-Net)<n> Experiments on HOT2020 and HOT2023 demonstrate MSP-Net achieves AUC and Precision exceeding 0.80 and 0.96, respectively.
  arXiv  Detail & Related papers  (2026-08-10T13:09:25Z)
• LESSViT: Robust Hyperspectral Representation Learning under Spectral Configuration Shift [29.791943499456426]
  Low-rank Efficient Spatial-Spectral ViT (LESSViT) is a sensor-flexible architecture for cross-spectral generalization.<n>We introduce a hyperspectral masked autoencoder (HyperMAE) with decoupled spatial-spectral masking and hierarchical channel sampling.
  arXiv  Detail & Related papers  (2026-05-18T15:22:26Z)
• Spectral Dynamic Attention Network for Hyperspectral Image Super-Resolution [45.72534786125302]
  Spectral Dynamic Attention Network (SDANet) is a framework designed to adaptively suppress redundant spectral interactions.<n>It achieves state-of-the-art HISR performance while maintaining competitive efficiency.
  arXiv  Detail & Related papers  (2026-04-30T02:13:33Z)
• A Synergistic CNN-Transformer Network with Pooling Attention Fusion for Hyperspectral Image Classification [10.687430702802608]
  In hyperspectral image (HSI) classification, each pixel is categorized into a specific land-cover category or material.<n>Recent works have utilized a multi-scale vision transformer (ViT) to enhance spectral feature capture and yield promising results.<n>We propose a synergistic CNN-Transformer network with pooling attention fusion for HSI classification.
  arXiv  Detail & Related papers  (2026-04-26T09:30:27Z)
• GCRPNet: Graph-Enhanced Contextual and Regional Perception Network for Salient Object Detection in Optical Remote Sensing Images [68.33481681452675]
  We propose a graph-enhanced contextual and regional perception network (GCRPNet)<n>It builds upon the Mamba architecture to simultaneously capture long-range dependencies and enhance regional feature representation.<n>It performs adaptive patch scanning on feature maps processed via multi-scale convolutions, thereby capturing rich local region information.
  arXiv  Detail & Related papers  (2025-08-14T11:31:43Z)
• Spatial-Geometry Enhanced 3D Dynamic Snake Convolutional Neural Network for Hyperspectral Image Classification [12.168520751389622]
  Deep neural networks face several challenges in hyperspectral image classification.<n>These include complex and sparse ground object distributions, small clustered structures, and elongated multi-branch features.<n>This paper proposes a Spatial-Geometry Enhanced 3D Dynamic Snake Network (SG-DSCNet) based on an improved 3D-DenseNet model.
  arXiv  Detail & Related papers  (2025-04-06T12:21:39Z)
• Efficient High-Resolution Visual Representation Learning with State Space Model for Human Pose Estimation [60.80423207808076]
  Capturing long-range dependencies while preserving high-resolution visual representations is crucial for dense prediction tasks such as human pose estimation.<n>We propose the Dynamic Visual State Space (DVSS) block, which augments visual state space models with multi-scale convolutional operations.<n>We build HRVMamba, a novel model for efficient high-resolution representation learning.
  arXiv  Detail & Related papers  (2024-10-04T06:19:29Z)
• Approaching Deep Learning through the Spectral Dynamics of Weights [41.948042468042374]
  spectral dynamics of weights -- the behavior of singular values and vectors during optimization -- to clarify and unify several phenomena in deep learning. We identify a consistent bias in optimization across various experiments, from small-scale grokking'' to large-scale tasks like image classification with ConvNets, image generation with UNets, speech recognition with LSTMs, and language modeling with Transformers.
  arXiv  Detail & Related papers  (2024-08-21T17:48:01Z)
• Hybrid Convolutional and Attention Network for Hyperspectral Image Denoising [54.110544509099526]
  Hyperspectral image (HSI) denoising is critical for the effective analysis and interpretation of hyperspectral data. We propose a hybrid convolution and attention network (HCANet) to enhance HSI denoising. Experimental results on mainstream HSI datasets demonstrate the rationality and effectiveness of the proposed HCANet.
  arXiv  Detail & Related papers  (2024-03-15T07:18:43Z)
• Salient Object Detection in Optical Remote Sensing Images Driven by Transformer [69.22039680783124]
  We propose a novel Global Extraction Local Exploration Network (GeleNet) for Optical Remote Sensing Images (ORSI-SOD) Specifically, GeleNet first adopts a transformer backbone to generate four-level feature embeddings with global long-range dependencies. Extensive experiments on three public datasets demonstrate that the proposed GeleNet outperforms relevant state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-09-15T07:14:43Z)
• RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images [82.1679766706423]
  Salient object detection (SOD) for optical remote sensing images (RSIs) aims at locating and extracting visually distinctive objects/regions from the optical RSIs. We propose a relational reasoning network with parallel multi-scale attention for SOD in optical RSIs. Our proposed RRNet outperforms the existing state-of-the-art SOD competitors both qualitatively and quantitatively.
  arXiv  Detail & Related papers  (2021-10-27T07:18:32Z)
• Cross-Attention in Coupled Unmixing Nets for Unsupervised Hyperspectral Super-Resolution [79.97180849505294]
  We propose a novel coupled unmixing network with a cross-attention mechanism, CUCaNet, to enhance the spatial resolution of HSI. Experiments are conducted on three widely-used HS-MS datasets in comparison with state-of-the-art HSI-SR models.
  arXiv  Detail & Related papers  (2020-07-10T08:08:20Z)

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.