Papers › DAFA: Diversity-Aware Feature Aggregation for Attention-Based Video Object Detection

DAFA: Diversity-Aware Feature Aggregation for Attention-Based Video Object Detection

1 Sep 2022IEEE Access 2022 9archive 2025-07-28

Si-Dong Roh, Ki-Seok Chung

We present a framework for attention-based video object detection using a simple yet effective external memory management algorithm. An attention mechanism has been adopted in video object detection task to enrich the features of key frames using adjacent frames. Although several recent studies utilized frame-level first-in-first-out (FIFO) memory to collect global video information, such a memory structure suffers from collection inefficiency, which results in low attention performance and high computational cost. To address this issue, we developed a novel scheme called diversity-aware feature aggregation (DAFA). Whereas other methods do not store sufficient feature information without expanding memory capacity, DAFA efficiently collects diverse features while avoiding redundancy using a simple Euclidean distance-based metric. Experimental results on the ImageNet VID dataset demonstrate that our lightweight model with global attention achieves 83.5 mAP on the ResNet-101 backbone, which exceeds the accuracy levels of most existing methods with a minimum runtime. Our method with global and local attention stages obtains 84.5 and 85.9 mAP on ResNet-101 and ResNeXt-101, respectively, thus achieving state-of-the-art performance without requiring additional post-processing methods.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiversityManagementObject DetectionVideo Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Object Detection ImageNet VID DAFA-F (ResNeXt-101) MAP 85.9 #12 of 33 Archive leaderboard report
Video Object Detection ImageNet VID DAFA-F (ResNet-101) MAP 84.5 #17 of 33 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections