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
• Authors: Guoyi Zhang, Siyang Chen, Guangsheng Xu, Han Wang, Xiaohu Zhang,
• 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

• 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)
• 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)

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.