SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.11124 · 2024

Cross-Task Affinity Learning for Multitask Dense Scene Predictions

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Multitask learning (MTL) has become prominent for its ability to predict multiple tasks jointly, achieving better per-task performance with fewer parameters than single-task learning. Recently, decoder-focused architectures have significantly improved multitask performance by refining task predictions using features from related tasks. However, most refinement methods struggle to efficiently capture both local and long-range dependencies between task-specific representations and cross-task patterns. In this paper, we introduce the Cross-Task Affinity Learning (CTAL) module, a lightweight framework that enhances task refinement in multitask networks. CTAL effectively captures local and long-range cross-task interactions by optimizing task affinity matrices for parameter-efficient grouped convolutions without concern for information loss. Our results demonstrate state-of-the-art MTL performance for both CNN and transformer backbones, using significantly fewer parameters than single-task learning. Our code is publicly available at https://github.com/Armanfard-Lab/EMA-Net.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2401.11124")
get_code_for_paper("2401.11124")
have("2401.11124")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2401.11124.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2401.11124.svg)](https://syntology.ai/paper/2401.11124)

Connect an agent — have() is free.