arXiv Machine Learning July 8, 2026 By Kerri Lu, Dan M. Kluger, Stephen Bates, Sherrie Wang

Conformal Prediction Sets for Instance Segmentation

Read the original on arXiv Machine Learning →

arXiv:2602. 10045v2 Announce Type: replace-cross Abstract: Current instance segmentation models achieve high performance on average predictions, but lack principled uncertainty quantification: their outputs are not calibrated, and there is no guarantee that a predicted mask is close to the ground truth.

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

computer-vision

arXiv AI

Jun 9

GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence

arXiv:2606. 08014v1 Announce Type: cross Abstract: Accurate 3D instance segmentation in point cloud data is critical for machine vision applications.

By Liang Xu, Fangjing Wang, Jinyu Yang, Feng Zheng

computer-vision benchmarks safety

arXiv AI

Jul 1

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models

arXiv:2606. 31603v1 Announce Type: cross Abstract: Semantic segmentation models struggle with data sparsity and rare or visually diverse regions, e.

By Nikolai R\"ohrich, Julian Glei{\ss}ner, Ahmed H. A. Ibrahim, Silvan Mertes, Tobias Huber

agents diffusion computer-vision fine-tuning efficiency safety

Hugging Face Trending Papers

Jun 24

Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Models

The computational complexity of Transformers scales quadratically with the number of tokens, which significantly constrains the efficiency of vision models, particularly recent ViT-based foundation models in dense prediction tasks. Instance segmentation, a typical dense visual prediction task in the remote sensing field, faces similar challenges.

llms computer-vision efficiency benchmarks

arXiv Machine Learning

Jun 9

SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests

arXiv:2606. 08206v1 Announce Type: cross Abstract: We present SegmentAnyTreeV2, a sensor- and platform-agnostic framework for semantic and instance segmentation of forest point clouds.

By Maciej Wielgosz, Stefano Puliti, Rasmus Astrup

llms computer-vision benchmarks

arXiv AI

Jun 2

Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks

arXiv:2606. 01947v1 Announce Type: cross Abstract: Research and applications in artificial intelligence have recently shifted with the rise of large pretrained models, which deliver state-of-the-art results across numerous tasks.

By Nermeen Abou Baker, David Rohrschneider, Uwe Handmann

llms computer-vision fine-tuning benchmarks

Hugging Face Trending Papers

Jul 2

Rethinking Post-Hoc Calibration in Semantic Segmentation

Reliable confidence estimates are essential in semantic segmentation, especially in safety-critical settings where overconfident errors can mislead downstream decisions. Yet modern segmentation models often remain miscalibrated.

computer-vision benchmarks safety

Related stories

GVC-Seg: Training-Free 3D Instance Segmentation via Geometric Visual Correspondence

Preserve the Hard, Regenerate the Rest: Uncertainty-Guided Synthetic Training Data Augmentation with Diffusion Models

Efficient Remote Sensing Instance Segmentation with Linear-Time State Space Distilled Visual Foundation Models

SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests

Parameter-Efficient Fine-Tuning of Large Pretrained Models for Instance Segmentation Tasks

Rethinking Post-Hoc Calibration in Semantic Segmentation