List your company
ResearchFormerly WizWand

Research

Papers for “ade20k”

Find papers, implementations, and the benchmark evidence behind state-of-the-art AI systems.

TitleAuthorsYearSource
FaPN: Feature-aligned Pyramid Network for Dense Image PredictionShihua Huang, Zhichao Lu, Ran Cheng2021arxiv 2108.07058
Fully Transformer Networks for Semantic Image SegmentationSitong Wu, Tianyi Wu, Fangjian Lin2021arxiv 2106.04108
SegRet: An Efficient Design for Semantic Segmentation with Retentive NetworkZhiyuan Li, Yi Chang, Yuan Wu2025arxiv 2502.14014
Efficient Self-Ensemble for Semantic SegmentationWalid Bousselham, Guillaume Thibault, Lucas Pagano2021arxiv 2111.13280
InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data PruningZiheng Qin, Kai Wang, Zangwei Zheng2023arxiv 2303.04947
SWAT: Spatial Structure Within and Among TokensKumara Kahatapitiya, Michael S. Ryoo2021arxiv 2111.13677
Scale Equalization for Multi-Level Feature FusionBum Jun Kim, Sang Woo Kim2024arxiv 2402.01149
Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic SegmentationZhengyuan Xie, Haiquan Lu, Jia-wen Xiao2024arxiv 2407.14142
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTsDonghyun Kim, Byeongho Heo, Dongyoon Han2024arxiv 2403.19588
SOS: Segment Object System for Open-World Instance Segmentation With Object PriorsChristian Wilms, Tim Rolff, Maris Hillemann2024arxiv 2409.14627
iFormer: Integrating ConvNet and Transformer for Mobile ApplicationChuanyang Zheng2025arxiv 2501.15369
Near, far: Patch-ordering enhances vision foundation models' scene understandingValentinos Pariza, Mohammadreza Salehi, Gertjan Burghouts2024arxiv 2408.11054
CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained AlignmentEdson Araujo, Andrew Rouditchenko, Yuan Gong2025arxiv 2505.01237
Convolution-based Probability Gradient Loss for Semantic SegmentationGuohang Shan, Shuangcheng Jia2024arxiv 2404.06704
DFormer: Diffusion-guided Transformer for Universal Image SegmentationHefeng Wang, Jiale Cao, Rao Muhammad Anwer2023arxiv 2306.03437
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision TransformersChenyang Lu, Daan de Geus, Gijs Dubbelman2023arxiv 2306.02095
COSNet: A Novel Semantic Segmentation Network using Enhanced Boundaries in Cluttered ScenesMuhammad Ali, Mamoona Javaid, Mubashir Noman2024arxiv 2410.24139
Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component AnalysisRachel S.Y. Teo, Tan M. Nguyen2024arxiv 2406.13762
Token Turing Machines are Efficient Vision ModelsPurvish Jajal, Nick John Eliopoulos, Benjamin Shiue-Hal Chou2024arxiv 2409.07613
ContextFormer: Redefining Efficiency in Semantic SegmentationMian Muhammad Naeem Abid, Nancy Mehta, Zongwei Wu2025arxiv 2501.19255