DINOv2-powered Few-Shot Semantic Segmentation: A Unified Framework via Cross-Model Distillation and 4D Correlation Mining

• URL: http://arxiv.org/abs/2504.15669v1
• Date: Tue, 22 Apr 2025 07:47:06 GMT
• Title: DINOv2-powered Few-Shot Semantic Segmentation: A Unified Framework via Cross-Model Distillation and 4D Correlation Mining
• Authors: Wei Zhuo, Zhiyue Tang, Wufeng Xue, Hao Ding, Linlin Shen,
• Abstract summary: Few-shot semantic segmentation has gained increasing interest due to its generalization capability.<n>Recent approaches have turned to foundation models to enhance representation transferability.<n>We propose FS-DINO, with only DINOv2's encoder and a lightweight segmenter.
• Score: 30.564216896513596
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Few-shot semantic segmentation has gained increasing interest due to its generalization capability, i.e., segmenting pixels of novel classes requiring only a few annotated images. Prior work has focused on meta-learning for support-query matching, with extensive development in both prototype-based and aggregation-based methods. To address data scarcity, recent approaches have turned to foundation models to enhance representation transferability for novel class segmentation. Among them, a hybrid dual-modal framework including both DINOv2 and SAM has garnered attention due to their complementary capabilities. We wonder "can we build a unified model with knowledge from both foundation models?" To this end, we propose FS-DINO, with only DINOv2's encoder and a lightweight segmenter. The segmenter features a bottleneck adapter, a meta-visual prompt generator based on dense similarities and semantic embeddings, and a decoder. Through coarse-to-fine cross-model distillation, we effectively integrate SAM's knowledge into our lightweight segmenter, which can be further enhanced by 4D correlation mining on support-query pairs. Extensive experiments on COCO-20i, PASCAL-5i, and FSS-1000 demonstrate the effectiveness and superiority of our method.

Related papers

• DSU-Net:An Improved U-Net Model Based on DINOv2 and SAM2 with Multi-scale Cross-model Feature Enhancement [7.9006143460465355]
  This paper proposes a multi-scale feature collabora-tion framework guided by DINOv2 for SAM2, with core innovations in three aspects.<n>It surpasses existing state-of-the-art meth-ods in downstream tasks such as camouflage target detection and salient ob-ject detection, without requiring costly training processes.
  arXiv  Detail & Related papers  (2025-03-27T06:08:24Z)
• TAVP: Task-Adaptive Visual Prompt for Cross-domain Few-shot Segmentation [40.49924427388922]
  We propose a task-adaptive auto-visual prompt framework for Cross-dominan Few-shot segmentation (CD-FSS) We incorporate a Class Domain Task-Adaptive Auto-Prompt (CDTAP) module to enable class-domain feature extraction and generate high-quality, learnable visual prompts. Our model outperforms the state-of-the-art CD-FSS approach, achieving an average accuracy improvement of 1.3% in the 1-shot setting and 11.76% in the 5-shot setting.
  arXiv  Detail & Related papers  (2024-09-09T07:43:58Z)
• Dual-scale Enhanced and Cross-generative Consistency Learning for Semi-supervised Medical Image Segmentation [49.57907601086494]
  Medical image segmentation plays a crucial role in computer-aided diagnosis. We propose a novel Dual-scale Enhanced and Cross-generative consistency learning framework for semi-supervised medical image (DEC-Seg)
  arXiv  Detail & Related papers  (2023-12-26T12:56:31Z)
• AM-RADIO: Agglomerative Vision Foundation Model -- Reduce All Domains Into One [47.58919672657824]
  We name this approach AM-RADIO (Agglomerative Model -- Reduce All Domains Into One) We develop a novel architecture (E-RADIO) that exceeds the performance of its predecessors and is at least 7x faster than the teacher models. Our comprehensive benchmarking process covers downstream tasks including ImageNet classification, ADE20k semantic segmentation, COCO object detection and LLaVa-1.5 framework.
  arXiv  Detail & Related papers  (2023-12-10T17:07:29Z)
• Semantic-SAM: Segment and Recognize Anything at Any Granularity [83.64686655044765]
  We introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity. We consolidate multiple datasets across three granularities and introduce decoupled classification for objects and parts. For the multi-granularity capability, we propose a multi-choice learning scheme during training, enabling each click to generate masks at multiple levels.
  arXiv  Detail & Related papers  (2023-07-10T17:59:40Z)
• Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract [47.85056124410376]
  Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. We design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. We propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation.
  arXiv  Detail & Related papers  (2023-06-27T08:10:20Z)
• Hierarchical Dense Correlation Distillation for Few-Shot Segmentation [46.696051965252934]
  Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. We design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. We propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation.
  arXiv  Detail & Related papers  (2023-03-26T08:13:12Z)
• Learning What Not to Segment: A New Perspective on Few-Shot Segmentation [63.910211095033596]
  Recently few-shot segmentation (FSS) has been extensively developed. This paper proposes a fresh and straightforward insight to alleviate the problem. In light of the unique nature of the proposed approach, we also extend it to a more realistic but challenging setting.
  arXiv  Detail & Related papers  (2022-03-15T03:08:27Z)
• Partner-Assisted Learning for Few-Shot Image Classification [54.66864961784989]
  Few-shot Learning has been studied to mimic human visual capabilities and learn effective models without the need of exhaustive human annotation. In this paper, we focus on the design of training strategy to obtain an elemental representation such that the prototype of each novel class can be estimated from a few labeled samples. We propose a two-stage training scheme, which first trains a partner encoder to model pair-wise similarities and extract features serving as soft-anchors, and then trains a main encoder by aligning its outputs with soft-anchors while attempting to maximize classification performance.
  arXiv  Detail & Related papers  (2021-09-15T22:46:19Z)
• SCNet: Enhancing Few-Shot Semantic Segmentation by Self-Contrastive Background Prototypes [56.387647750094466]
  Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples. Most of advanced solutions exploit a metric learning framework that performs segmentation through matching each pixel to a learned foreground prototype. This framework suffers from biased classification due to incomplete construction of sample pairs with the foreground prototype only.
  arXiv  Detail & Related papers  (2021-04-19T11:21:47Z)
• MetaDistiller: Network Self-Boosting via Meta-Learned Top-Down Distillation [153.56211546576978]
  In this work, we propose that better soft targets with higher compatibil-ity can be generated by using a label generator. We can employ the meta-learning technique to optimize this label generator. The experiments are conducted on two standard classificationbenchmarks, namely CIFAR-100 and ILSVRC2012.
  arXiv  Detail & Related papers  (2020-08-27T13:04:27Z)

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.