Vision-Centric Representation-Efficient Fine-Tuning for Robust Universal Foreground Segmentation

• URL: http://arxiv.org/abs/2504.14481v1
• Date: Sun, 20 Apr 2025 04:12:38 GMT
• Title: Vision-Centric Representation-Efficient Fine-Tuning for Robust Universal Foreground Segmentation
• Abstract summary: Foreground segmentation is crucial for scene understanding, yet parameter-efficient fine-tuning (PEFT) of vision foundation models (VFMs) often fails in complex scenarios.<n>We propose Ladder Shape-bias Representation Side-tuning (LSR-ST), a lightweight PEFT framework that enhances model robustness by introducing shape-biased inductive priors.
• Score: 5.326302374594885
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foreground segmentation is crucial for scene understanding, yet parameter-efficient fine-tuning (PEFT) of vision foundation models (VFMs) often fails in complex scenarios, such as camouflage and infrared imagery. We attribute this challenge to the inherent texture bias in VFMs, which is exacerbated during fine-tuning and limits generalization in texture-sparse environments. To address this, we propose Ladder Shape-bias Representation Side-tuning (LSR-ST), a lightweight PEFT framework that enhances model robustness by introducing shape-biased inductive priors. LSR-ST captures shape-aware features using a simple HDConv Block, which integrates large-kernel attention and residual learning. The method satisfies three key conditions for inducing shape bias: large receptive fields, multi-order feature interactions, and sparse connectivity. Our analysis reveals that these improvements stem from representation efficiency-the ability to extract task-relevant, structurally grounded features while minimizing redundancy. We formalize this concept via Information Bottleneck theory and advocate for it as a key PEFT objective. Unlike traditional NLP paradigms that focus on optimizing parameters and memory, visual tasks require models that extract task-defined semantics, rather than just relying on pre-encoded features. This shift enables our approach to move beyond conventional trade-offs, offering more robust and generalizable solutions for vision tasks. With minimal changes to SAM2-UNet, LSR-ST achieves consistent improvements across 17 datasets and 6 tasks using only 4.719M trainable parameters. These results highlight the potential of representation efficiency for robust and adaptable VFMs within complex visual environments.

Related papers

• FAIR: Feature-Augmented Implicit Regularization for AI-generated Fake Image Detection [5.673956549751241]
  Generalization remains a critical bottleneck in AI-generated image detection.<n>We propose Feature-Augmented Implicit Regularization (FAIR)<n>We show that FAIR boosts accuracy by up to 8.04% and establishes new state-of-the-art robustness in zero-shot transfer scenarios.
  arXiv  Detail & Related papers  (2026-07-24T08:34:56Z)
• LCPNet: Latent Consistent Proximal Unfolding Network for Infrared Small Target Detection [50.3892176822492]
  Infrared small target detection (IRSTD) aims to identify long distance small targets from complex infrared backgrounds.<n>Deep learning methods have improved IRSTD by learning discriminative image-to-mask mappings.<n>Deep unfolding methods partially address this issue by embedding model-driven iterations into neural networks.<n>We propose Latent Consistent Proximal unfolding network (LCPNet) to address these limitations.
  arXiv  Detail & Related papers  (2026-07-06T02:15:09Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• 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)
• StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models [98.72926158261937]
  We propose a training-free token pruning framework for Visual AutoRegressive models.<n>We employ a lightweight high-pass filter to capture local texture details, while leveraging Principal Component Analysis (PCA) to preserve global structural information.<n>To maintain valid next-scale prediction under sparse tokens, we introduce a nearest neighbor feature propagation strategy.
  arXiv  Detail & Related papers  (2026-03-02T11:35:05Z)
• You Only Look Omni Gradient Backpropagation for Moving Infrared Small Target Detection [4.782962269769956]
  We propose BP-FPN, a backpropagation-driven feature pyramid architecture for small target detection.<n>The design is theoretically grounded, negligible computational introduces overhead, and can be seamlessly integrated into existing frameworks.<n>Extensive experiments on multiple public datasets show that BP-FPN consistently establishes new state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-11-17T06:13:41Z)
• Rethinking Evaluation of Infrared Small Target Detection [105.59753496831739]
  This paper introduces a hybrid-level metric incorporating pixel- and target-level performance, proposing a systematic error analysis method, and emphasizing the importance of cross-dataset evaluation.<n>An open-source toolkit has be released to facilitate standardized benchmarking.
  arXiv  Detail & Related papers  (2025-09-21T02:45:07Z)
• Beyond Motion Cues and Structural Sparsity: Revisiting Small Moving Target Detection [5.375165101682048]
  Small moving target detection is crucial for many defense applications.<n>However, it remains highly challenging due to low signal-to-noise ratios, ambiguous visual cues, and cluttered backgrounds.<n>We propose a novel deep learning framework that differs fundamentally from existing approaches.
  arXiv  Detail & Related papers  (2025-09-09T12:20:25Z)
• FOAM: A General Frequency-Optimized Anti-Overlapping Framework for Overlapping Object Perception [7.258172311752019]
  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.<n>We propose a general Frequency-based Anti-Overlapping Framework (FOAM) to assist the model in extracting more texture and contour information.<n>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.
  arXiv  Detail & Related papers  (2025-06-16T13:58:49Z)
• AuxDet: Auxiliary Metadata Matters for Omni-Domain Infrared Small Target Detection [58.67129770371016]
  We propose a novel IRSTD framework that reimagines the IRSTD paradigm by incorporating textual metadata for scene-aware optimization.<n>AuxDet consistently outperforms state-of-the-art methods, validating the critical role of auxiliary information in improving robustness and accuracy.
  arXiv  Detail & Related papers  (2025-05-21T07:02:05Z)
• End-to-End Vision Tokenizer Tuning [73.3065542220568]
  The vision tokenizer optimized for low-level reconstruction is to downstream tasks requiring varied representations and semantics.<n>The loss of the vision tokenization can be the representation bottleneck for target tasks.<n>We propose ETT, an end-to-end vision tokenizer tuning approach that enables joint optimization between vision tokenization and target autoregressive tasks.
  arXiv  Detail & Related papers  (2025-05-15T17:59:39Z)
• CSPENet: Contour-Aware and Saliency Priors Embedding Network for Infrared Small Target Detection [4.731073701194089]
  Infrared small target detection (ISTD) plays a critical role in a wide range of civilian and military applications.<n>Existing methods suffer from deficiencies in the localization of dim targets and the perception of contour information under dense clutter environments.<n>We propose a contour-aware and saliency priors embedding network (CSPENet) for ISTD.
  arXiv  Detail & Related papers  (2025-05-15T03:56:36Z)
• Back to Fundamentals: Low-Level Visual Features Guided Progressive Token Pruning [8.284127681482202]
  'LVTP' is a progressive token pruning framework guided by multi-scale Tsallis entropy and low-level visual features with twice clustering. It integrates high-level semantics and basic visual attributes for precise segmentation. As a plug-and-play module, it requires no architectural changes or additional training.
  arXiv  Detail & Related papers  (2025-04-25T00:43:20Z)
• CFMD: Dynamic Cross-layer Feature Fusion for Salient Object Detection [7.262250906929891]
  Cross-layer feature pyramid networks (CFPNs) have achieved notable progress in multi-scale feature fusion and boundary detail preservation for salient object detection.<n>To address these challenges, we propose CFMD, a novel cross-layer feature pyramid network that introduces two key innovations.<n>First, we design a context-aware feature aggregation module (CFLMA), which incorporates the state-of-the-art Mamba architecture to construct a dynamic weight distribution mechanism.<n>Second, we introduce an adaptive dynamic upsampling unit (CFLMD) that preserves spatial details during resolution recovery.
  arXiv  Detail & Related papers  (2025-04-02T03:22:36Z)
• ContextFormer: Redefining Efficiency in Semantic Segmentation [48.81126061219231]
  Convolutional methods, although capturing local dependencies well, struggle with long-range relationships.<n>Vision Transformers (ViTs) excel in global context capture but are hindered by high computational demands.<n>We propose ContextFormer, a hybrid framework leveraging the strengths of CNNs and ViTs in the bottleneck to balance efficiency, accuracy, and robustness for real-time semantic segmentation.
  arXiv  Detail & Related papers  (2025-01-31T16:11:04Z)
• Efficient Detection Framework Adaptation for Edge Computing: A Plug-and-play Neural Network Toolbox Enabling Edge Deployment [59.61554561979589]
  Edge computing has emerged as a key paradigm for deploying deep learning-based object detection in time-sensitive scenarios.<n>Existing edge detection methods face challenges: difficulty balancing detection precision with lightweight models, limited adaptability, and insufficient real-world validation.<n>We propose the Edge Detection Toolbox (ED-TOOLBOX), which utilizes generalizable plug-and-play components to adapt object detection models for edge environments.
  arXiv  Detail & Related papers  (2024-12-24T07:28:10Z)
• MCGS: Multiview Consistency Enhancement for Sparse-View 3D Gaussian Radiance Fields [73.49548565633123]
  Radiance fields represented by 3D Gaussians excel at synthesizing novel views, offering both high training efficiency and fast rendering. Existing methods often incorporate depth priors from dense estimation networks but overlook the inherent multi-view consistency in input images. We propose a view framework based on 3D Gaussian Splatting, named MCGS, enabling scene reconstruction from sparse input views.
  arXiv  Detail & Related papers  (2024-10-15T08:39:05Z)
• SOLO: A Single Transformer for Scalable Vision-Language Modeling [74.05173379908703]
  We present SOLO, a single transformer for visiOn-Language mOdeling.<n>A unified single Transformer architecture, like SOLO, effectively addresses these scalability concerns in LVLMs.<n>In this paper, we introduce the first open-source training recipe for developing SOLO, an open-source 7B LVLM.
  arXiv  Detail & Related papers  (2024-07-08T22:40:15Z)
• Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models [32.83187649097727]
  We build a dataset of over four million multi-view image-text pairs across more than 100K objects. We design a novel fine-tuning framework named Omniview-Tuning (OVT) OVT introduces a Cross-Viewpoint Alignment objective through a minimax-like optimization strategy.
  arXiv  Detail & Related papers  (2024-04-18T12:41:33Z)
• Parameter Hierarchical Optimization for Visible-Infrared Person Re-Identification [0.6675805308519986]
  Visible-infrared person re-identification (VI-reID) aims at matching cross-modality pedestrian images captured by disjoint visible or infrared cameras. We propose a novel parameter optimizing paradigm, parameter hierarchical optimization (PHO) method, for the task of VI-ReID. It allows part of parameters to be directly optimized without any training, which narrows the search space of parameters and makes the whole network more easier to be trained.
  arXiv  Detail & Related papers  (2024-04-11T17:27:39Z)
• Distance Weighted Trans Network for Image Completion [52.318730994423106]
  We propose a new architecture that relies on Distance-based Weighted Transformer (DWT) to better understand the relationships between an image's components. CNNs are used to augment the local texture information of coarse priors. DWT blocks are used to recover certain coarse textures and coherent visual structures.
  arXiv  Detail & Related papers  (2023-10-11T12:46:11Z)
• Can SAM Boost Video Super-Resolution? [78.29033914169025]
  We propose a simple yet effective module -- SAM-guidEd refinEment Module (SEEM) This light-weight plug-in module is specifically designed to leverage the attention mechanism for the generation of semantic-aware feature. We apply our SEEM to two representative methods, EDVR and BasicVSR, resulting in consistently improved performance with minimal implementation effort.
  arXiv  Detail & Related papers  (2023-05-11T02:02:53Z)
• Semantic-aware Modular Capsule Routing for Visual Question Answering [55.03883681191765]
  We propose a Semantic-aware modUlar caPsulE framework, termed as SUPER, to better capture the instance-specific vision-semantic characteristics. We comparatively justify the effectiveness and generalization ability of our proposed SUPER scheme over five benchmark datasets.
  arXiv  Detail & Related papers  (2022-07-21T10:48:37Z)
• Progressive Self-Guided Loss for Salient Object Detection [102.35488902433896]
  We present a progressive self-guided loss function to facilitate deep learning-based salient object detection in images. Our framework takes advantage of adaptively aggregated multi-scale features to locate and detect salient objects effectively.
  arXiv  Detail & Related papers  (2021-01-07T07:33:38Z)
• Attentional Local Contrast Networks for Infrared Small Target Detection [15.882749652217653]
  We propose a novel model-driven deep network for infrared small target detection. We modularize a conventional local contrast measure method as a depth-wise parameterless nonlinear feature refinement layer in an end-to-end network. We conduct detailed ablation studies with varying network depths to empirically verify the effectiveness and efficiency of each component in our network architecture.
  arXiv  Detail & Related papers  (2020-12-15T19:33:09Z)

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.