Conditional Random Fields

Also known as CRF

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 12

All topics

CRF Loss is How Networks Should Learn Boundaries in Weakly Supervised Segmentation
Sep 28, 2026Joshua Li, Yuri BoykovConditional Random Fields Weakly Supervised Semantic Segmentation
Cheriton School of Computer Science University of Waterloo
UnfoldCRF: Structured Mask Refinement with Image-Conditioned Latent Regions
Sep 27, 2026Chunming He, Rihan Zhang, Lei Xu +5Image Segmentation Conditional Random Fields
Duke University · EPFL · National University of Singapore +2
Whole-Slide Image Analysis under Realistic Few-Shot Annotation Protocols
Aug 31, 2026Tiffanie Godelaine, Maxime Zanella, Karim El Khoury +2Computational Pathology Conditional Random Fields
Institute of Information and Communication Technologies, Electronics, and Applied Mathematics (ICTEAM), Université catholique de Louvain (UCLouvain), 1348 Louvain-la-Neuve, Belgium
Federated Learning with Energy-Based Structured Probabilistic Inference
Jun 29, 2026Dario Fenoglio, Daniil Kirilenko, Martin Gjoreski +1Federated Learning Aggregation Conditional Random Fields
Faculty of Informatics, Universit`a della Svizzera italiana, Lugano, Switzerland.
SenFlow: Inter-Sentence Flow Modeling for AI-Generated Text Detection in Hybrid Documents
Jun 17, 2026Jingkun Luo, Yifan Sun, Da-Tian Peng +1AI-Generated Text Detection Conditional Random Fields
Northwestern Polytechnical University · Zhejiang Lab
Approximate Structured Diffusion for Sequence Labelling
Jun 17, 2026Nicolas Floquet, Joseph Le Roux, Nadi TomehConditional Random Fields Morphosyntactic Tagging
Université Sorbonne Paris Nord, CNRS, Laboratoire d’Informatique de Paris Nord, LIPN, F-93430 Villetaneuse, France
A Lightweight Hybrid Transformer-CRF Architecture for Multi-Type Bangla Medical Entity Recognition
May 25, 2026Peyal Saha, Ahsanul Haque Hasib, Shoumik Barman PolokNamed Entity Recognition Conditional Random Fields
Dept. of CSE KUET, Khulna, Bangladesh
Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning
May 14, 2026Jingjing Wang, Xiwen Chen, Wenhui Zhu +6LLM Pruning AI Coding Agents
Clemson University · Morgan Stanley · Arizona State University +1
Exploring the Potential of Probabilistic Transformer for Time Series Modeling: A Report on the ST-PT Framework
Apr 29, 2026Zhangzhi Xiong, Haoyi Wu, You Wu +3Transformer Conditional Random Fields
School of Information Science and Technology, ShanghaiTech University
ESIA: An Energy-Based Spatiotemporal Interaction-Aware Framework for Pedestrian Intention Prediction
Apr 26, 2026Yanping Wu, Meiting Dang, Lin Wu +3Pedestrian Intention Prediction Pedestrian Behavior Modeling
James Watt School of Engineering, University of Glasgow, Glasgow, G12 8QQ, United Kingdom · School of Computing Science, University of Glasgow, Glasgow, G12 8QQ, United Kingdom
Streaming Structured Inference with Flash-SemiCRF
Apr 20, 2026Benjamin K. Johnson, Thomas Goralski, Ayush Semwal +2Efficient Inference Conditional Random Fields
Department of Epigenetics, Van Andel Institute, 333 Bostwick Ave. NE, Grand Rapids, 49503, MI, USA. · Department of Cell Biology, Van Andel Institute, 333 Bostwick Ave. NE, Grand Rapids, 49503, MI, USA.
PPEDCRF: Dynamic-CRF-Guided Selective Perturbation for Background-Based Location Privacy in Video Sequences
Apr 18, 2026Bo Ma, Weiqi Yan, Jinsong WuConditional Random Fields Adversarial Perturbations
Resideo Technologies Inc., Scottsdale, Arizona, USA · Auckland University of Technology, Auckland, New Zealand · Guilin University of Electronic Technology, Guilin, China

Sep 28, 2026, cs.CVJ/K move · Enter open · S save

CRF Loss is How Networks Should Learn Boundaries in Weakly Supervised Segmentation

Joshua Li, Yuri Boykov

Cheriton School of Computer Science University of Waterloo

Conditional Random Fields Weakly Supervised Semantic Segmentation Boundary-Aware Segmentation

Open paper AskPDF arXiv

Weakly Supervised Semantic Segmentation (WSSS) learns pixel-level predictions from image-level tags. Recent work focuses on improving coarse CAMs extracted from large vision-language models (commonly CLIP), but does little to improve their accuracy along segment boundaries. That job is instead delegated to a post-processing method like DenseCRF. However, because DenseCRF relies on low-level colour cues, it can flip correct labels to incorrect ones when neighbouring pixels share similar colours. SAM has recently been adopted as a natural alternative, yet it simply takes on DenseCRF's role as an intermediate "refinement" step that outputs one-hot pseudo-labels in prior work. By discarding the valuable uncertainty in CAMs, these one-hot pseudo-labels turn borderline errors into confidently wrong targets. Our key insight is that CAMs should supervise training alongside SAM boundaries, each through its own loss, rather than being fused together into a single hard target. Inspired by CRF potentials, we propose a framework that disentangles soft pseudo-labels as unary supervision and binary edge maps as pairwise supervision. We realize our framework in a single-stage model, DS-CRF, using CAMs from dino.txt and boundaries from SAM. DS-CRF sets a new state-of-the-art of 56.5% mIoU on MS COCO.

Momentum

Related topics

Latest papers 12