arXiv AI August 10, 2026 By Yonglong Zhang, Zongwu Xie, Yang Liu

GeoDistill-Refine: Silhouette-First Geometry Distillation for Annotation-Free Spacecraft Segmentation

arXiv:2608. 07405v1 Announce Type: cross Abstract: Foundation segmentation models can provide supervision for spacecraft imagery without manual training masks, but their predictions vary with textual prompts and may contain geometric errors that are amplified during distillation.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 16

Post-Launch Capability Expansion of Vision-Language Models via Prompting for On-Orbit Spacecraft Inspection

arXiv:2606. 15427v1 Announce Type: cross Abstract: Spaceborne inspection systems often deploy perception models prior to launch, after which updating model weights or expanding fixed label sets becomes operationally impractical.

By Nicholas A. Welsh, Lennon J. Shikhman, Monty Nehru Attazs, Seemanthini K. Putane, Van Minh Nguyen, Ryan T. White

llms computer-vision multimodal

arXiv AI

Jul 7

GeoSelect: Spatial-Program Execution for Training-Free Referring Remote Sensing Image Segmentation

arXiv:2607. 03869v1 Announce Type: cross Abstract: Referring remote sensing image segmentation isolates the object named by a natural-language expression in an aerial image.

By Yuhang Jiang, Guohui Deng, Miaozhong Xu, Chao Ruan, Jinling Zhao, Linsheng Huang

llms computer-vision multimodal

arXiv AI

Jun 30

RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation

arXiv:2606. 28410v1 Announce Type: cross Abstract: Open-vocabulary semantic segmentation (OVSS) enables text-guided segmentation of unseen objects, breaking fixed-class limitations to achieve open-world understanding.

By Shanwen Wang, Xin Sun, Sirui Wang, Xiao Xiang Zhu

llms computer-vision benchmarks safety

arXiv Machine Learning

Aug 11

Contrastive Mask Fidelity: Reference-Free Auditing of Ground-Truth Masks in Remote Sensing Semantic Segmentation

arXiv:2608. 09101v1 Announce Type: cross Abstract: Semantic segmentation models are trained and evaluated against human-drawn masks, yet remote-sensing annotations are often coarse, incomplete, or misaligned; high overlap scores may then reflect agreement with imperfect labels rather than faithfulness to the image, creating an evaluation paradox.

By Shuaishuai Cao, Shuwei Peng, Meng Tang, Min Huang, Youjin Wang, Jie Chen, Jing Ouyang, Zhiwei Zhai

computer-vision multimodal benchmarks

arXiv AI

Jun 16

Mask Proposal Voting Based on Geodesic Framework for Robust Image Segmentation

arXiv:2606. 14912v1 Announce Type: cross Abstract: Despite great advances, finding accurate segmentation remains a challenging task, especially in scenarios with cluttered backgrounds, complex intensity variations and topology appearance.

By Li Liu, Mingzhu Wang, Zhenjiang Li, Da Chen, Laurent D. Cohen

computer-vision benchmarks

arXiv Machine Learning

Jun 4

Spatially Grounded Concept Bottleneck Models via Part-Factorized Attention

arXiv:2606. 04364v1 Announce Type: cross Abstract: Concept bottleneck models (CBMs) predict a layer of human-named attributes before predicting a class, which makes their decisions auditable.

By Dhanesh Ramachandram

llms computer-vision

Related stories

Post-Launch Capability Expansion of Vision-Language Models via Prompting for On-Orbit Spacecraft Inspection

GeoSelect: Spatial-Program Execution for Training-Free Referring Remote Sensing Image Segmentation

RSGPNet: Geometric Prompting for Remote Sensing Open-Vocabulary Semantic Segmentation

Contrastive Mask Fidelity: Reference-Free Auditing of Ground-Truth Masks in Remote Sensing Semantic Segmentation

Mask Proposal Voting Based on Geodesic Framework for Robust Image Segmentation

Spatially Grounded Concept Bottleneck Models via Part-Factorized Attention