Cover Image

DeGMix: Efficient Multi-Task Dense Prediction with Deformable and Gating Mixer

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Xu, Yangyang, Yang, Yibo, Ghanem, Bernard, Zhang, Lefei, Du, Bo, Zhu, Jun
Format:	Preprint
Published:	2023
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-Task Dense Prediction Fine-Tuning with Mixture of Fine-Grained Experts
by: Xu, Yangyang, et al.
Published: (2025)

Multi-Task Dense Prediction via Mixture of Low-Rank Experts
by: Yang, Yuqi, et al.
Published: (2024)

Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
by: Shen, Li, et al.
Published: (2024)

Efficient Domain-Adaptive Multi-Task Dense Prediction with Vision Foundation Models
by: Kang, Beomseok, et al.
Published: (2025)

ChebMixer: Efficient Graph Representation Learning with MLP Mixer
by: Kui, Xiaoyan, et al.
Published: (2024)

Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions
by: Zhang, Jingdong, et al.
Published: (2024)

SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries
by: Mkhallati, Hassan, et al.
Published: (2023)

MTLSI-Net: A Linear Semantic Interaction Network for Parameter-Efficient Multi-Task Dense Prediction
by: Liu, Chen, et al.
Published: (2026)

$\mathcal{B}^{3}$-Net: Controlled Posterior Bridge Learning for Multi-Task Dense Prediction
by: Zhou, Meihua, et al.
Published: (2026)

Enhancing Mamba Decoder with Bidirectional Interaction in Multi-Task Dense Prediction
by: Cao, Mang, et al.
Published: (2025)

Task Indicating Transformer for Task-conditional Dense Predictions
by: Lu, Yuxiang, et al.
Published: (2024)

ResidualViT for Efficient Temporally Dense Video Encoding
by: Soldan, Mattia, et al.
Published: (2025)

MGIMM: Multi-Granularity Instruction Multimodal Model for Attribute-Guided Remote Sensing Image Detailed Description
by: Yang, Cong, et al.
Published: (2024)

GateMOT: Q-Gated Attention for Dense Object Tracking
by: Lv, Mingjin, et al.
Published: (2026)

GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning
by: Li, Xiaojie, et al.
Published: (2024)

Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing
by: Xu, Yangyang, et al.
Published: (2024)

ATOM: Attention Mixer for Efficient Dataset Distillation
by: Khaki, Samir, et al.
Published: (2024)

UniUIR: Considering Underwater Image Restoration as An All-in-One Learner
by: Zhang, Xu, et al.
Published: (2025)

$β$-CLIP: Text-Conditioned Contrastive Learning for Multi-Granular Vision-Language Alignment
by: Zohra, Fatimah, et al.
Published: (2025)

Progressive Growing of Patch Size: Resource-Efficient Curriculum Learning for Dense Prediction Tasks
by: Fischer, Stefan M., et al.
Published: (2024)

A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image Classification
by: Liu, Quanwei, et al.
Published: (2024)

MambaHSI: Spatial-Spectral Mamba for Hyperspectral Image Classification
by: Li, Yapeng, et al.
Published: (2025)

Centroid-centered Modeling for Efficient Vision Transformer Pre-training
by: Yan, Xin, et al.
Published: (2023)

RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything
by: Xu, Shilin, et al.
Published: (2024)

Multi-modal Auto-regressive Modeling via Visual Words
by: Peng, Tianshuo, et al.
Published: (2024)

TrackMAE: Video Representation Learning via Track Mask and Predict
by: Vandeghen, Renaud, et al.
Published: (2026)

BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
by: Liu, Shuming, et al.
Published: (2025)

A Vanilla Multi-Task Framework for Dense Visual Prediction Solution to 1st VCL Challenge -- Multi-Task Robustness Track
by: Chen, Zehui, et al.
Published: (2024)

BiDense: Binarization for Dense Prediction
by: Yin, Rui, et al.
Published: (2024)

Enhancing Online Continual Learning with Plug-and-Play State Space Model and Class-Conditional Mixture of Discretization
by: Liu, Sihao, et al.
Published: (2024)

Video Self-Stitching Graph Network for Temporal Action Localization
by: Zhao, Chen, et al.
Published: (2020)

MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention
by: Zhao, Zilong, et al.
Published: (2026)

Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization
by: Fontana, Maxime, et al.
Published: (2024)

OFL-SAM2: Prompt SAM2 with Online Few-shot Learner for Efficient Medical Image Segmentation
by: Lan, Meng, et al.
Published: (2025)

FFNet: MetaMixer-based Efficient Convolutional Mixer Design
by: Yun, Seokju, et al.
Published: (2024)

EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
by: Cai, Han, et al.
Published: (2022)

Multi-Tailed Vision Transformer for Efficient Inference
by: Wang, Yunke, et al.
Published: (2022)

Progressive Retinal Image Registration via Global and Local Deformable Transformations
by: Liu, Yepeng, et al.
Published: (2024)

Vivid-ZOO: Multi-View Video Generation with Diffusion Model
by: Li, Bing, et al.
Published: (2024)

Memory Efficient Transformer Adapter for Dense Predictions
by: Zhang, Dong, et al.
Published: (2025)