Cover Image

Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Yi, Xu, Xin, Li, Jian, Hu, Xiaochang, Shi, Yifei, Zeng, Ling-Li
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

Fluid Dynamic DNNs for Reliable and Adaptive Distributed Inference on Edge Devices
by: Xun, Lei, et al.
Published: (2024)

Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded Devices
by: Xun, Lei, et al.
Published: (2024)

Learning Positive-Incentive Point Sampling in Neural Implicit Fields for Object Pose Estimation
by: Shi, Yifei, et al.
Published: (2026)

TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge
by: Kwon, Young D., et al.
Published: (2023)

Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modeling
by: Li, Yuan-Ming, et al.
Published: (2023)

Predicting and Enhancing the Fairness of DNNs with the Curvature of Perceptual Manifolds
by: Ma, Yanbiao, et al.
Published: (2023)

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

Gradient Similarity Surgery in Multi-Task Deep Learning
by: Borsani, Thomas, et al.
Published: (2025)

Conditional Representation Learning for Customized Tasks
by: Liu, Honglin, et al.
Published: (2025)

Uncertainty-aware Prototype Learning with Variational Inference for Few-shot Point Cloud Segmentation
by: Zhao, Yifei, et al.
Published: (2026)

Learning Domain-Aware Task Prompt Representations for Multi-Domain All-in-One Image Restoration
by: Dong, Guanglu, et al.
Published: (2026)

FIELDS: Face reconstruction with accurate Inference of Expression using Learning with Direct Supervision
by: Ling, Chen, et al.
Published: (2025)

Rep-MTL: Unleashing the Power of Representation-level Task Saliency for Multi-Task Learning
by: Wang, Zedong, et al.
Published: (2025)

All-In-One Medical Image Restoration via Task-Adaptive Routing
by: Yang, Zhiwen, et al.
Published: (2024)

Data-driven Verification of DNNs for Object Recognition
by: Otte, Clemens, et al.
Published: (2024)

Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators
by: Azizi, Seyedarmin, et al.
Published: (2024)

SplatFlow: Learning Multi-frame Optical Flow via Splatting
by: Wang, Bo, et al.
Published: (2023)

Is Class Signal Clustered or Routed in Task-Induced Implicit Neural Representation Weight Spaces?
by: Guo, Xinyi, et al.
Published: (2026)

Task-Driven Prompt Learning: A Joint Framework for Multi-modal Cloud Removal and Segmentation
by: Zhang, Zaiyan, et al.
Published: (2026)

Unveiling and Mitigating Generalized Biases of DNNs through the Intrinsic Dimensions of Perceptual Manifolds
by: Ma, Yanbiao, et al.
Published: (2024)

Mamba Learns in Context: Structure-Aware Domain Generalization for Multi-Task Point Cloud Understanding
by: Jiang, Jincen, et al.
Published: (2026)

Integrating Amortized Inference with Diffusion Models for Learning Clean Distribution from Corrupted Images
by: Wang, Yifei, et al.
Published: (2024)

NVSPolicy: Adaptive Novel-View Synthesis for Generalizable Language-Conditioned Policy Learning
by: Shi, Le, et al.
Published: (2025)

Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses
by: Fang, Hao, et al.
Published: (2024)

MotionHiFlow: Text-to-motion via hierarchical flow matching
by: Li, Heng, et al.
Published: (2026)

u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model
by: Xu, Jinjin, et al.
Published: (2023)

[CLS] is Not Enough: Multi-Label Recognition via Patch-Level Inference and Adaptive Aggregation
by: Wang, Akang, et al.
Published: (2026)

Progressive Human Motion Generation Based on Text and Few Motion Frames
by: Zeng, Ling-An, et al.
Published: (2025)

DeCLIP: Decoupled Prompting for CLIP-based Multi-Label Class-Incremental Learning
by: Du, Kaile, et al.
Published: (2025)

Semantic Routing: Exploring Multi-Layer LLM Feature Weighting for Diffusion Transformers
by: Li, Bozhou, et al.
Published: (2026)

Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs
by: Li, Mingjie, et al.
Published: (2023)

Sparse-Tuning: Adapting Vision Transformers with Efficient Fine-tuning and Inference
by: Liu, Ting, et al.
Published: (2024)

Gradients Stand-in for Defending Deep Leakage in Federated Learning
by: Yi, H., et al.
Published: (2024)

Learning from Noise: Enhancing DNNs for Event-Based Vision through Controlled Noise Injection
by: Kowalczyk, Marcin, et al.
Published: (2025)

Understanding Retrieval-Augmented Task Adaptation for Vision-Language Models
by: Ming, Yifei, et al.
Published: (2024)

Progressive Pretext Task Learning for Human Trajectory Prediction
by: Lin, Xiaotong, et al.
Published: (2024)

What Your Features Reveal: Data-Efficient Black-Box Feature Inversion Attack for Split DNNs
by: Ren, Zhihan, et al.
Published: (2025)

One at a Time: Progressive Multi-step Volumetric Probability Learning for Reliable 3D Scene Perception
by: Li, Bohan, et al.
Published: (2023)

OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learning
by: Yang, Zhengwei, et al.
Published: (2026)

Learning to Generate Gradients for Test-Time Adaptation via Test-Time Training Layers
by: Deng, Qi, et al.
Published: (2024)