# Liquid Fusion of Heterogeneous Representations Towards General Salient Object Detection

arXiv: https://arxiv.org/abs/2606.26849 · HTML: https://mlsanity.com/paper/2606.26849/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 41 of its 80 references that are in the map.
- First posted on arXiv 25 Jun 2026.

## Builds on (most cited first, 30 of 41)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Visual Saliency Based on Multiscale Deep Features](https://mlsanity.com/paper/1503.08663/) (2015)
- [Visual Saliency Transformer](https://mlsanity.com/paper/2104.12099/) (2021)
- [Liquid Time-constant Networks](https://mlsanity.com/paper/2006.04439/) (2020)
- [PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition](https://mlsanity.com/paper/2403.17695/) (2024)
- [Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks](https://mlsanity.com/paper/1907.06781/) (2019)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [RS-Mamba for Large Remote Sensing Image Dense Prediction](https://mlsanity.com/paper/2404.02668/) (2024)
- [Highly Efficient Salient Object Detection with 100K Parameters](https://mlsanity.com/paper/2003.05643/) (2020)
- [JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection](https://mlsanity.com/paper/2004.08515/) (2020)
- [Full-Duplex Strategy for Video Object Segmentation](https://mlsanity.com/paper/2108.03151/) (2021)
- [Sigma: Siamese Mamba Network for Multi-Modal Semantic Segmentation](https://mlsanity.com/paper/2404.04256/) (2024)
- [Specificity-preserving RGB-D Saliency Detection](https://mlsanity.com/paper/2108.08162/) (2021)
- [RGBT Salient Object Detection: A Large-scale Dataset and Benchmark](https://mlsanity.com/paper/2007.03262/) (2020)
- [Closed-form Continuous-time Neural Models](https://mlsanity.com/paper/2106.13898/) (2021)
- [EDN: Salient Object Detection via Extremely-Downsampled Network](https://mlsanity.com/paper/2012.13093/) (2020)
- [SwinNet: Swin Transformer drives edge-aware RGB-D and RGB-T salient object detection](https://mlsanity.com/paper/2204.05585/) (2022)
- [RGB-T Image Saliency Detection via Collaborative Graph Learning](https://mlsanity.com/paper/1905.06741/) (2019)
- [VSCode: General Visual Salient and Camouflaged Object Detection with 2D Prompt Learning](https://mlsanity.com/paper/2311.15011/) (2023)
- [A Unified RGB-T Saliency Detection Benchmark: Dataset, Baselines, Analysis and A Novel Approach](https://mlsanity.com/paper/1701.02829/) (2017)
- [A Unified Transformer Framework for Group-based Segmentation: Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection](https://mlsanity.com/paper/2203.04708/) (2022)
- [DPANet: Depth Potentiality-Aware Gated Attention Network for RGB-D Salient Object Detection](https://mlsanity.com/paper/2003.08608/) (2020)
- [MaIR: A Locality- and Continuity-Preserving Mamba for Image Restoration](https://mlsanity.com/paper/2412.20066/) (2024)
- [Does Thermal Really Always Matter for RGB-T Salient Object Detection?](https://mlsanity.com/paper/2210.04266/) (2022)

## Abstract (arXiv)

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.