Dense Prediction

Follow this topic Ask about this topic

Dense prediction studies how models assign meaningful outputs to every pixel, patch, or grid cell, supporting tasks such as segmentation, depth estimation, pose, and weather forecasting. Common approaches combine multi-scale CNN or transformer features with task-specific decoders, while self-supervised pretraining, distillation, and foundation-model adaptation aim to improve transfer across tasks and domains. Evaluation spans benchmarks such as Cityscapes and ADE20K for segmentation, COCO for detection and pose, and KITTI or NYUD-v2 for depth. Current work seeks to retain fine spatial detail while reducing compute and adapting to varied data, with a continuing tension between unified models and specialized systems.

Latest papers

31 papers5 papers in the last four weeks, up 25% on the four weeks before. 0.0% of all new papers.

CODI: Improving Self-Supervised Vision Transformers with Cross Distillation
Oct 22, 2026Siran Dai, Qianqian Xu, Peisong Wen +3Vision Transformer Self-Supervised Visual Representation Learning
Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences · State Key Laboratory of AI Safety, Institute of Computing Technology, CAS +3
Supervision-Adaptive Curriculum and Guarded Anti-Curriculum Learning for Dense Prediction
Oct 21, 2026Chunming He, Dingming Zhang, Fengyang Xiao +2Curriculum Learning Dense Prediction
Department of Biomedical Engineering, Duke University, Durham, NC 27708 USA · Adobe Inc., San Jose, CA, USA
Unlocking Fine-Grained Perception in CLIP via Structurally-Aware Latent Masked Modeling
Oct 6, 2026Juntong Li, Lingwei Dang, Haomin Wu +3VLM Adaptation Dense Prediction
School of Software Engineering, South China University of Technology
PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion
Sep 30, 2026Lehan Yang, Daiqing Qi, Wenhao Zhang +9Diffusion Model Alignment Diffusion Transformer
University of Virginia · Michigan State University · Adobe +1
Decoupling Spherical Reasoning from Dense Prediction for 360 Depth Estimation
Sep 30, 2026Zhijie Shen, Chunyu Lin, Shuai Zheng +4Graph Neural Networks Depth Estimation
Beijing Jiaotong University · Hefei University of Technology · Shandong University
Scalable In-Domain Self-Supervised Foundation Model for Dense Representation Transfer in High-Resolution Plant Imaging
Sep 26, 2026Junlin Guo, Sharmin Majumder, Isaac Lyngaas +2Vision Foundation Models Self-Supervised Pre-Training
Oak Ridge National Laboratory Oak Ridge, TN, USA
GTR: Gated Token Recurrence for Efficient Dense Prediction
Sep 22, 2026Zhe Feng, Longfei Liu, Wei Liu +7Efficient Neural Network Inference Gated Attention
Didi International Business Group · Intellindust AI Lab · Institute of Automation, Chinese Academy of Sciences +2
LiFR v2: Completion-Augmented Event Propagation for High-Rate Dense Prediction
Sep 22, 2026Tao Wan, Xiaoshan Wu, Yifei Yu +6Event-Based Vision Monocular Depth Estimation
School of Microelectronics, Southern University of Science and Technology, Shenzhen 518055, China · Department of Electrical and Computer Engineering, The University of Hong Kong, Hong Kong, China
SPARC: SuperPixel-Aware Region Contrastive Learning for Self-Supervised Dense Prediction
Sep 16, 2026David Szczecina, Yuanpei Xiang, Jitao Hu +4Self-Supervised Visual Representation Learning Contrastive Learning
Systems Design Engineering University of Waterloo Waterloo, Ontario, Canada
GramLoop: Training-Free Gram-Gated Replay for Robust Dense Prediction
Aug 29, 2026Yang Chen, Canyu Shen, Xinzhe Rao +5Distribution Shift Robustness Test-Time Adaptation
Huazhong University of Science and Technology · Tongji University · King Abdullah University of Science and Technology +2
HSMLA: Hierarchical Softmax Multi-scale Linear Attention for Efficient Vision Transformers
Aug 7, 2026Dong Liu, Yanxuan Yu, Renata Borovica-Gajic +2Efficient ViTs Linear Attention
University of California, Los Angeles, USA · Columbia University, USA · The University of Melbourne, Australia +1
Benchmarking Deep Learning Models for Dense Event Classification of Offshore Wind Infrastructure in Sentinel-1 Time Series
Aug 5, 2026Thorsten Hoeser, Felix Bachofer, Claudia KuenzerTime Series Classification Recurrent Neural Networks
Earth Observation Center (EOC), German Aerospace Center (DLR), Oberpfaffenhofen, 82234 Wessling, Germany · Institute for Geography and Geology, University of Wuerzburg, 97074 Wuerzburg, Germany
Unified Video Dense Prediction from Disjoint Data
Jul 23, 2026Yihong Sun, Seoung Wug Oh, Jiahui Huang +2Multi-Task Learning Dense Prediction
Adobe Research · Cornell University
Think Sparse, Predict Dense: Continuous Thought Machines for Image Super-Resolution
Jul 21, 2026Zekai ShiDense Prediction Image Super-Resolution
Xi’an Jiaotong University
EA-RMENet -- Path Loss Prediction in Urban Environments using Deep Learning
Jul 17, 2026Jonathan O'Shea, Conor BrennanRadio Propagation Modeling Dense Prediction
DCU School of Electronic Engineering
From RGB Generation to Dense Field Readout: Pixel-Space Dense Prediction with Text-to-Image Models
Jul 7, 2026Zanyi Wang, Xin Lin, Haodong Li +2Diffusion Transformer Dense Prediction
1UCSD · 2HKUST
Less Tokens, Better Forecasts: Sparse Residual Routing for Efficient Weather Prediction
Jul 2, 2026Janet Wang, Yunbei Zhang, Lin Zhao +3Efficient ViTs Dense Prediction
Tulane University · Northeastern University · University of Alabama at Birmingham +1
MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense Prediction
Jun 29, 2026Shuo Zhou, Zhaoxin Li, Xiujuan ChaiMonocular Depth Estimation Surface Normal Estimation
Agricultural Information Institute, Chinese Academy of Agricultural Sciences, Beijing, China. · Key Laboratory of Agricultural Big Data, Ministry of Agriculture and Rural Affairs, Beijing, China.
UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and Perception
Jun 29, 2026Qin Guo, Hao Luo, Dongxu Yue +4Diffusion Transformer Dense Prediction
The Hong Kong University of Science and Technology · DAMO Academy, Alibaba Group, Zhejiang, China · Hupan Lab, Zhejiang Province +4
RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation
Jun 22, 2026Yuchuan Ding, Linfei Li, Lin Zhang +1Dense Prediction
School of Computer Science and Technology, Tongji University, Shanghai, China
Phase Marginalization for Patch-Grid Instability in Vision Transformers
Jun 6, 2026Oğuzhan ErcanVision Transformer Dense Prediction
Scientific and Technological Research Council of Türkiye
SIGMA: Bridging Structural and Distributional Gaps for Vision Foundation Model Adaptation
May 27, 2026Lingyu Xiong, Jinjin Shi, Xuran Xu +3Vision Foundation Model Adaptation Dense Prediction
Xiaomi Corporation
Phase-Aware Wavelet-Based-Scattering Encoder-Decoder for Dense Predictions
May 23, 2026Ghassen Marrakchi, Basarab MateiWavelet Methods Wavelet Scattering Transforms
Northern Paris Computer Science Lab, Sorbonne Paris Nord University, Villetaneuse, France.
Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores
May 12, 2026Alan Z. Song, Yinjie Chen, Mu Nan +3Visual Representation Learning Vision Transformer
Carnegie Mellon University · University of Hong Kong
$\mathcal{B}^{3}$ -Net: Controlled Posterior Bridge Learning for Multi-Task Dense Prediction
May 7, 2026Meihua Zhou, Li YangMulti-Task Learning Dense Prediction
Wannan Medical University, Wuhu, China · University of Chinese Academy of Sciences, Beijing, China
RADMI: Latent Information Aggregation as a Proxy for Model Uncertainty
May 2, 2026William Stevens, Mohit Prabhushankar, Ghassan AlRegibUncertainty Quantification Dense Prediction
OLIVES at the Center for Signal and Information Processing, School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA
Sapiens2
Apr 23, 2026Rawal Khirodkar, He Wen, Julieta Martinez +3Vision Foundation Models Human Pose Estimation
Meta Reality Labs
A3-FPN: Asymptotic Content-Aware Pyramid Attention Network for Dense Visual Prediction
Apr 11, 2026Meng'en Qin, Yu Song, Quanling Zhao +3Dense Prediction Multi-Scale Feature Fusion
Henan Engineering Research Center for Artificial Intelligence Theory and Algorithms, Henan University, Kaifeng, China · Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology, Shenzhen, China · Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, China
HAD: Heterogeneity-Aware Distillation for Lifelong Heterogeneous Learning
Mar 27, 2026Xuerui Zhang, Xuehao Wang, Zhan Zhuang +5Knowledge Distillation Dense Prediction
Southern University of Science and Technology · Technical University of Munich · Zhejiang University +2
EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation
Mar 19, 2026Longfei Liu, Yongjie Hou, Yang Li +7Dense Prediction Efficient ViTs
Intellindust AI Lab

Oct 22, 2026J/K move · Enter open · S save

CODI: Improving Self-Supervised Vision Transformers with Cross Distillation

Siran Dai, Qianqian Xu, Peisong Wen, Yang Liu+2

Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences · State Key Laboratory of AI Safety, Institute of Computing Technology, CAS+3

Vision Transformer Self-Supervised Visual Representation Learning Self-Supervised Knowledge Distillation Dense Prediction Knowledge Distillation

Open paper AskPDF arXiv

Self-supervised Vision Transformers learn strong image-level representations, but their patch-level representations can be unreliable for dense prediction. We study this mismatch and find that the class token concentrates global semantics on a small number of representative patches, while dense prediction errors often occur on low-attention regions. We provide a local gradient analysis showing that, along the [CLS] attention readout, image-level self-distillation gradients are weighted by [CLS]-to-patch attention mass. To provide masked patches with global semantics without changing the architecture, we propose Cross Distillation (CODI), which mixes a small amount of the teacher class-token distribution into each teacher patch-token target. CODI gives every masked patch an attention-independent semantic correction while preserving the standard self-distillation architecture. Experiments on dense and image-level benchmarks show that CODI improves both dense and image-level performance under aligned pretraining settings. Code is available at https://github.com/EldercatSAM/CODI.