Better than Average: Spatially-Aware Aggregation of Segmentation Uncertainty Improves Downstream Performance
Max-Delbrück-Center (MDC)（马克斯·德尔布吕克中心）；Helmholtz Imaging（亥姆霍兹成像）；Charité Universitätsmedizin（柏林夏里特医学院）；Humboldt-Universität zu Berlin（柏林洪堡大学）；University of Potsdam（波茨坦大学）；German Cancer Research Center (DKFZ)（德国癌症研究中心）；Heidelberg University（海德堡大学）
Vanessa Emanuela Guarino, Claudia Winklmayr, Jannik Franzen, Josef Lorenz Rumberger, Manuel Pfeuffer, Sonja Greven, Klaus Maier-Hein, Carsten T. Lüth, Christoph… 展开作者
Vanessa Emanuela Guarino, Claudia Winklmayr, Jannik Franzen, Josef Lorenz Rumberger, Manuel Pfeuffer, Sonja Greven, Klaus Maier-Hein, Carsten T. Lüth, Christoph Karg, Dagmar Kainmueller
备注：
27 pages, 13 figures, 6 tables. Accepted at CVPR 2026 (The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026)
Uncertainty Quantification (UQ) is crucial for ensuring the reliability of automated image segmentations in safety-critical domains like biomedical image analysis or autonomous driving. In segmentation, UQ generates pixel-wise uncertainty scores that must be aggregated into image-level scores for downstream tasks like Out-of-Distribution (OoD) or failure detection. Despite routine use of aggregation strategies, their properties and impact on downstream task performance have not yet been comprehensively studied. Global Average is the default choice, yet it does not account for spatial and structural features of segmentation uncertainty. Alternatives like patch-, class- and threshold-based strategies exist, but lack systematic comparison, leading to inconsistent reporting and unclear best practices. We address this gap by (1) formally analyzing properties, limitations, and pitfalls of common strategies; (2) proposing novel strategies that incorporate spatial uncertainty structure and (3) benchmarking their performance on OoD and failure detection across ten datasets that vary in image geometry and structure. We find that aggregators leveraging spatial structure yield stronger performance in both downstream tasks studied. However, the performance of individual aggregators depends heavily on dataset characteristics, so we (4) propose a meta-aggregator that integrates multiple aggregators and performs robustly across datasets.
Spatially-guided Temporal Aggregation for Robust Event-RGB Optical Flow Estimation
Department of Automation, University of Science and Technology of China（自动化系，中国科学技术大学）；Department of Computer Science, City University of Hong Kong（计算机科学系，香港城市大学）；Department of Mechanical Engineering, City University of Hong Kong（机械工程系，香港城市大学）；College of Computer Science, Beijing University of Technology（计算机科学学院，北京理工大学）
Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While these contrastive methods mainly focus on generating invariant global representations at the image-level under semantic-preserving transformations, they are prone to overlook spatial consistency of local representations and therefore have a limitation in pretraining for localization tasks such as object detection and instance segmentation. Moreover, aggressi…
Satellite imagery and remote sensing provide explanatory variables at relatively high resolutions for modeling geospatial phenomena, yet regional summaries are often desirable for analysis and actionable insight. In this paper, we propose a novel method of inducing spatial aggregations as a component of the machine learning process, yielding regional model features whose construction is driven by model prediction performance rather than prior assumptions. Our results demonstrate that Genetic Programming is particularly well suited to this type of feature construction because it can automatical…
School of Information and Artificial Intelligence, Yunnan University of Finance and Economics（云南财经大学信息与人工智能学院）；Department of Computer Science, Hong Kong Baptist University（香港浸会大学计算机科学系）；School of Electronics and Information, Northwestern Polytechnical University（西北工业大学电子信息学院）
University of Washington（华盛顿大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Deep learning-based methods have achieved promising results on surgical instrument segmentation. However, the high computation cost may limit the application of deep models to time-sensitive tasks such as online surgical video analysis for robotic-assisted surgery. Moreover, current methods may still suffer from challenging conditions in surgical images such as various lighting conditions and the presence of blood. We propose a novel Multi-frame Feature Aggregation (MFFA) module to aggregate video frame features temporally and spatially in a recurrent mode. By distributing the computation load…
SenseTime Research（商汤科技研究院）；Harbin Institute of Technology（哈尔滨工业大学）；Nanjing University of Science and Technology（南京理工大学）
Nowadays stereo cameras are more commonly adopted in emerging devices such as dual-lens smartphones and unmanned aerial vehicles. However, they also suffer from blurry images in dynamic scenes which leads to visual discomfort and hampers further image processing. Previous works have succeeded in monocular deblurring, yet there are few studies on deblurring for stereoscopic images. By exploiting the two-view nature of stereo images, we propose a novel stereo image deblurring network with Depth Awareness and View Aggregation, named DAVANet. In our proposed network, 3D scene cues from the depth a…
Global Context-aware Representation Learning for Spatially Resolved Transcriptomics
Graduate School of Data Science, KAIST, Daejeon, Republic of Korea；Department of Industrial \& Systems Engineering, KAIST, Daejeon, Republic of Korea；Department of Mathematical Sciences, KAIST, Daejeon, Republic of Korea
Most convolutional neural networks (CNNs) for image classification use a global average pooling (GAP) followed by a fully-connected (FC) layer for output logits. However, this spatial aggregation procedure inherently restricts the utilization of location-specific information at the output layer, although this spatial information can be beneficial for classification. In this paper, we propose a novel spatial output layer on top of the existing convolutional feature maps to explicitly exploit the location-specific output information. In specific, given the spatial feature maps, we replace the pr…
Research institute for signals, systems and computational intelligence, sinc(i), FICH-UNL/CONICET（信号、系统与计算智能研究所 sinc(i)，FICH-UNL/CONICET）；University of Oxford（牛津大学）；TheraPanacea；CentraleSupelec（中央理工-高等电力学院）；Universite Paris-Saclay（巴黎-萨克雷大学）
Deformable registration has been one of the pillars of biomedical image computing. Conventional approaches refer to the definition of a similarity criterion that, once endowed with a deformation model and a smoothness constraint, determines the optimal transformation to align two given images. The definition of this metric function is among the most critical aspects of the registration process. We argue that incorporating semantic information (in the form of anatomical segmentation maps) into the registration process will further improve the accuracy of the results. In this paper, we propose a…
From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-Identification
Department of Electrical and Computer Engineering, University of Washington（华盛顿大学电气与计算机工程系）；Applied Physics Laboratory, University of Washington（华盛顿大学应用物理实验室）
Existing GAN inversion and editing methods work well for aligned objects with a clean background, such as portraits and animal faces, but often struggle for more difficult categories with complex scene layouts and object occlusions, such as cars, animals, and outdoor images. We propose a new method to invert and edit such complex images in the latent space of GANs, such as StyleGAN2. Our key idea is to explore inversion with a collection of layers, spatially adapting the inversion process to the difficulty of the image. We learn to predict the "invertibility" of different image segments and pr…
Information Technology University of Punjab（旁遮普信息技术大学）
Most of the recent Deep Semantic Segmentation algorithms suffer from large generalization errors, even when powerful hierarchical representation models based on convolutional neural networks have been employed. This could be attributed to limited training data and large distribution gap in train and test domain datasets. In this paper, we propose a multi-level self-supervised learning model for domain adaptation of semantic segmentation. Exploiting the idea that an object (and most of the stuff given context) should be labeled consistently regardless of its location, we generate spatially inde…
Scalable Training of Spatially Grounded 2D Vision-Language Models for Radiology
Computer Vision Group, University of Freiburg, Germany（德国弗莱堡大学计算机视觉组）；Department of Radiology, Medical Center -- University of Freiburg, Germany（德国弗莱堡大学医学中心放射科）；CRIION-AI Lab, Freiburg, Germany（德国弗莱堡CRIION-AI实验室）
Transformers have shown great success in medical image segmentation. However, transformers may exhibit a limited generalization ability due to the underlying single-scale self-attention (SA) mechanism. In this paper, we address this issue by introducing a Multi-scale hiERarchical vIsion Transformer (MERIT) backbone network, which improves the generalizability of the model by computing SA at multiple scales. We also incorporate an attention-based decoder, namely Cascaded Attention Decoding (CASCADE), for further refinement of multi-stage features generated by MERIT. Finally, we introduce an eff…
A large labeled dataset is a key to the success of supervised deep learning, but for medical image segmentation, it is highly challenging to obtain sufficient annotated images for model training. In many scenarios, unannotated images are abundant and easy to acquire. Self-supervised learning (SSL) has shown great potentials in exploiting raw data information and representation learning. In this paper, we propose Hierarchical Self-Supervised Learning (HSSL), a new self-supervised framework that boosts medical image segmentation by making good use of unannotated data. Unlike the current literatu…
ViCoR: Reliable Molecular Structure Extraction via Spatially Aligned Verification and Executable Revision
The Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong（香港中文大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
