# ASSD: Attentive Single Shot Multibox Detector

Source: [ASSD: Attentive Single Shot Multibox Detector](<https://www.sota2.com/research/paper/68fa66791e209131cea106bb>)

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

Data updated: 2025-10-25T21:50:28.993Z

Authors: Jingru Yi, Pengxiang Wu, Dimitris N. Metaxas

Published: 2019-09-27T01:36:41.000Z

## Abstract

This paper proposes a new deep neural network for object detection. The proposed network, termed ASSD, builds feature relations in the spatial space of the feature map. With the global relation information, ASSD learns to highlight useful regions on the feature maps while suppressing the irrelevant information, thereby providing reliable guidance for object detection. Compared to methods that rely on complicated CNN layers to refine the feature maps, ASSD is simple in design and is computationally efficient. Experimental results show that ASSD competes favorably with the state-of-the-arts, including SSD, DSSD, FSSD and RetinaNet.

## 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/1909.12456>)

[PDF](<https://arxiv.org/pdf/1909.12456.pdf>)
