Split-Fuse-Transport: Annotation-Free Saliency via Dual Clustering and Optimal Transport Alignment

• URL: http://arxiv.org/abs/2510.17484v1
• Date: Mon, 20 Oct 2025 12:27:55 GMT
• Title: Split-Fuse-Transport: Annotation-Free Saliency via Dual Clustering and Optimal Transport Alignment
• Abstract summary: Salient object detection (SOD) aims to segment visually prominent regions in images and serves as a foundational task for various computer vision applications.<n>We posit that SOD can now reach near-supervised accuracy without a single pixel-level label, but only when reliable pseudo-masks are available.<n>We introduce POTNet, an adaptation of Prototypical Optimal Transport that replaces POT's single k-means step with an entropy-guided dual-clustering head.<n>This split-fuse-transport design yields sharper, part-aware pseudo-masks in a single forward pass, without handcrafted priors.
• Score: 10.013879292840707
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Salient object detection (SOD) aims to segment visually prominent regions in images and serves as a foundational task for various computer vision applications. We posit that SOD can now reach near-supervised accuracy without a single pixel-level label, but only when reliable pseudo-masks are available. We revisit the prototype-based line of work and make two key observations. First, boundary pixels and interior pixels obey markedly different geometry; second, the global consistency enforced by optimal transport (OT) is underutilized if prototype quality is weak. To address this, we introduce POTNet, an adaptation of Prototypical Optimal Transport that replaces POT's single k-means step with an entropy-guided dual-clustering head: high-entropy pixels are organized by spectral clustering, low-entropy pixels by k-means, and the two prototype sets are subsequently aligned by OT. This split-fuse-transport design yields sharper, part-aware pseudo-masks in a single forward pass, without handcrafted priors. Those masks supervise a standard MaskFormer-style encoder-decoder, giving rise to AutoSOD, an end-to-end unsupervised SOD pipeline that eliminates SelfMask's offline voting yet improves both accuracy and training efficiency. Extensive experiments on five benchmarks show that AutoSOD outperforms unsupervised methods by up to 26% and weakly supervised methods by up to 36% in F-measure, further narrowing the gap to fully supervised models.

Related papers

• Exploring SAM Supervision for Fine-Grained UAV Target Segmentation under Data Scarcity [0.0]
  Unmanned aerial vehicle (UAV) target segmentation is challenging due to the small size of objects, appearance variations, cluttered backgrounds, and the scarcity of densely annotated data.<n>This paper investigates the use of SAM3 as a pseudo-label generator for training compact segmentation networks.
  arXiv  Detail & Related papers  (2026-07-04T07:59:10Z)
• Real-Time Source-Free Object Detection [40.10658212485104]
  Real-world detectors for autonomous driving, surveillance, and robotics must handle domain-shifts under strict latency and memory constraints.<n>We show that building on YOLOv10, an NMS-free dual-head detector, we achieve state-of-the-art adaptation accuracy while being faster and more compact.
  arXiv  Detail & Related papers  (2026-06-30T15:38:56Z)
• Exploring the Limits of End-to-End Feature-Affinity Propagation for Single-Point Supervised Infrared Small Target Detection [6.7126559398433665]
  Single-point supervised infrared small target detection (IRSTD) drastically reduces dense annotation costs.<n>Current state-of-the-art (SOTA) methods achieve high precision by recovering mask supervision through explicit, offline pseudo-label construction.<n>We study a minimalist alternative: generating point-to-mask supervision online through in-batch, point-anchored feature-affinity propagation.
  arXiv  Detail & Related papers  (2026-05-01T15:08:46Z)
• Point-to-Mask: From Arbitrary Point Annotations to Mask-Level Infrared Small Target Detection [11.256548408562894]
  Point-to-Mask is a framework that bridges low-cost point supervision and mask-level detection.<n>The proposed framework achieves strong pseudo-label quality, high detection accuracy, and efficient inference.
  arXiv  Detail & Related papers  (2026-03-17T08:44:05Z)
• Unsupervised Deformable Image Registration with Structural Nonparametric Smoothing [21.95149344518237]
  Learning-based deformable image registration (DIR) alignment accelerates by amortizing traditional optimization via neural networks.<n>We introduce SmoothProper, a plug-and-play neural module enforcing smoothness and promoting message passing within the network's forward pass.<n>Preliminary results on a retinal vessel dataset demonstrate our method reduces registration error to 1.88 pixels on 2912x2 images.
  arXiv  Detail & Related papers  (2025-06-12T15:26:03Z)
• Prior2Former -- Evidential Modeling of Mask Transformers for Assumption-Free Open-World Panoptic Segmentation [74.55677741919035]
  We propose Prior2Former (P2F), the first approach for segmentation vision transformers rooted in evidential learning.<n>P2F extends the mask vision transformer architecture by incorporating a Beta prior for computing model uncertainty in pixel-wise binary mask assignments.<n>Unlike most segmentation models addressing unknown classes, P2F operates without access to OOD data samples or contrastive training on void (i.e., unlabeled) classes.
  arXiv  Detail & Related papers  (2025-04-07T08:53:14Z)
• SAM-guided Pseudo Label Enhancement for Multi-modal 3D Semantic Segmentation [16.019735682706163]
  Multi-modal 3D semantic segmentation is vital for applications such as autonomous driving and virtual reality (VR)<n>To effectively deploy these models in real-world scenarios, it is essential to employ cross-domain adaptation techniques.<n>Self-training with pseudo-labels has emerged as a predominant method for cross-domain adaptation in 3D semantic segmentation.
  arXiv  Detail & Related papers  (2025-02-02T23:52:37Z)
• Bridge the Points: Graph-based Few-shot Segment Anything Semantically [79.1519244940518]
  Recent advancements in pre-training techniques have enhanced the capabilities of vision foundation models. Recent studies extend the SAM to Few-shot Semantic segmentation (FSS) We propose a simple yet effective approach based on graph analysis.
  arXiv  Detail & Related papers  (2024-10-09T15:02:28Z)
• Triple Point Masking [49.39218611030084]
  Existing 3D mask learning methods encounter performance bottlenecks under limited data. We introduce a triple point masking scheme, named TPM, which serves as a scalable framework for pre-training of masked autoencoders. Extensive experiments show that the four baselines equipped with the proposed TPM achieve comprehensive performance improvements on various downstream tasks.
  arXiv  Detail & Related papers  (2024-09-26T05:33:30Z)
• Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection [108.672972439282]
  We introduce a novel decoupled pseudo-labeling (DPL) approach for SSM3OD. Our approach features a Decoupled Pseudo-label Generation (DPG) module, designed to efficiently generate pseudo-labels. We also present a DepthGradient Projection (DGP) module to mitigate optimization conflicts caused by noisy depth supervision of pseudo-labels.
  arXiv  Detail & Related papers  (2024-03-26T05:12:18Z)
• Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost [53.746169882193456]
  Recent works have proposed various sparse attention modules to overcome the quadratic cost of self-attention. We propose a model that resolves both problems by endowing each attention head with a mixed-membership Block Model. Our model outperforms previous efficient variants as well as the original Transformer with full attention.
  arXiv  Detail & Related papers  (2022-10-27T15:30:52Z)
• Dynamic Prototype Mask for Occluded Person Re-Identification [88.7782299372656]
  Existing methods mainly address this issue by employing body clues provided by an extra network to distinguish the visible part. We propose a novel Dynamic Prototype Mask (DPM) based on two self-evident prior knowledge. Under this condition, the occluded representation could be well aligned in a selected subspace spontaneously.
  arXiv  Detail & Related papers  (2022-07-19T03:31:13Z)
• Model Inspired Autoencoder for Unsupervised Hyperspectral Image Super-Resolution [25.878793557013207]
  This paper focuses on hyperspectral image (HSI) super-resolution that aims to fuse a low-spatial-resolution HSI and a high-spatial-resolution multispectral image. Existing deep learning-based approaches are mostly supervised that rely on a large number of labeled training samples. We make the first attempt to design a model inspired deep network for HSI super-resolution in an unsupervised manner.
  arXiv  Detail & Related papers  (2021-10-22T05:15:16Z)
• Graph Regularized Autoencoder and its Application in Unsupervised Anomaly Detection [42.86693635734333]
  We propose to use a minimum spanning tree (MST) to approximate the local neighborhood structure and generate structure-preserving distances among data points. We develop a new graph regularized autoencoder, which outperforms a wide range of alternative methods over 20 benchmark anomaly detection datasets.
  arXiv  Detail & Related papers  (2020-10-29T21:17:41Z)

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.