SpaRTAN: Spatial Reinforcement Token-based Aggregation Network for Visual Recognition

TL;DR

SpaRTAN introduces a lightweight neural network architecture that enhances spatial and channel-wise feature processing using multi-scale kernels and wave-based channel aggregation, achieving high accuracy with fewer parameters in visual recognition tasks.

Contribution

The paper presents SpaRTAN, a novel architecture that effectively captures multi-order spatial features and reduces channel redundancies, improving efficiency and performance over existing models.

Findings

Achieves 77.7% accuracy on ImageNet-1k with only 3.8M parameters.

Surpasses previous benchmarks on COCO with 50.0% AP using 21.5M parameters.

Demonstrates high parameter efficiency and competitive performance in visual recognition.

Abstract

The resurgence of convolutional neural networks (CNNs) in visual recognition tasks, exemplified by ConvNeXt, has demonstrated their capability to rival transformer-based architectures through advanced training methodologies and ViT-inspired design principles. However, both CNNs and transformers exhibit a simplicity bias, favoring straightforward features over complex structural representations. Furthermore, modern CNNs often integrate MLP-like blocks akin to those in transformers, but these blocks suffer from significant information redundancies, necessitating high expansion ratios to sustain competitive performance. To address these limitations, we propose SpaRTAN, a lightweight architectural design that enhances spatial and channel-wise information processing. SpaRTAN employs kernels with varying receptive fields, controlled by kernel size and dilation factor, to capture discriminative multi-order spatial features effectively. A wave-based channel aggregation module further modulates and reinforces pixel interactions, mitigating channel-wise redundancies. Combining the two modules, the proposed network can efficiently gather and dynamically contextualize discriminative features. Experimental results in ImageNet and COCO demonstrate that SpaRTAN achieves remarkable parameter efficiency while maintaining competitive performance. In particular, on the ImageNet-1k benchmark, SpaRTAN achieves 77. 7% accuracy with only 3.8M parameters and approximately 1.0 GFLOPs, demonstrating its ability to deliver strong performance through an efficient design. On the COCO benchmark, it achieves 50.0% AP, surpassing the previous benchmark by 1.2% with only 21.5M parameters. The code is publicly available at [https://github.com/henry-pay/SpaRTAN].