# IvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules

Source: [IvaNet: Learning to jointly detect and segment objets with the help of Local Top-Down Modules](<https://www.sota2.com/research/paper/68fa65871e209131cea0ae2d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:56:38.389Z

Authors: Shihua Huang, Lu Wang

Published: 2019-03-18T10:58:54.000Z

## Abstract

Driven by Convolutional Neural Networks, object detection and semantic segmentation have gained significant improvements. However, existing methods on the basis of a full top-down module have limited robustness in handling those two tasks simultaneously. To this end, we present a joint multi-task framework, termed IvaNet. Different from existing methods, our IvaNet backwards abstract semantic information from higher layers to augment lower layers using local top-down modules. The comparisons against some counterparts on the PASCAL VOC and MS COCO datasets demonstrate the functionality of IvaNet.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1903.07360>)

[PDF](<https://arxiv.org/pdf/1903.07360.pdf>)