# EffiPerception: an Efficient Framework for Various Perception Tasks

Source: [EffiPerception: an Efficient Framework for Various Perception Tasks](<https://www.sota2.com/research/paper/68fa728f1e209131cea5713a>)

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

Data updated: 2025-10-27T06:31:06.454Z

Authors: Xinhao Xiang, Simon Dr\\"ager, Jiawei Zhang

Published: 2024-03-18T23:22:37.000Z

## Abstract

The accuracy-speed-memory trade-off is always the priority to consider for several computer vision perception tasks.   Previous methods mainly focus on a single or small couple of these tasks, such as creating effective data augmentation, feature extractor, learning strategies, etc. These approaches, however, could be inherently task-specific: their proposed model's performance may depend on a specific perception task or a dataset.   Targeting to explore common learning patterns and increasing the module robustness, we propose the EffiPerception framework.   It could achieve great accuracy-speed performance with relatively low memory cost under several perception tasks: 2D Object Detection, 3D Object Detection, 2D Instance Segmentation, and 3D Point Cloud Segmentation.   Overall, the framework consists of three parts:   (1) Efficient Feature Extractors, which extract the input features for each modality. (2) Efficient Layers, plug-in plug-out layers that further process the feature representation, aggregating core learned information while pruning noisy proposals. (3) The EffiOptim, an 8-bit optimizer to further cut down the computational cost and facilitate performance stability.   Extensive experiments on the KITTI, semantic-KITTI, and COCO datasets revealed that EffiPerception could show great accuracy-speed-memory overall performance increase within the four detection and segmentation tasks, in comparison to earlier, well-respected methods.

## 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/2403.12317>)

[PDF](<https://arxiv.org/pdf/2403.12317.pdf>)
