Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
The paper introduces RDCNet, a novel image classification architecture based on ResNet-34, designed to improve fine-grained feature extraction and background noise suppression. RDCNet incorporates Multi-Branch Random Dilated Convolution (MRDC), Fine-Grained Feature Enhancement (FGFE), and Context Excitation (CE) modules to capture multi-scale contextual information and enhance robustness. Experiments on five benchmark datasets demonstrate that RDCNet achieves state-of-the-art classification accuracy, outperforming competing methods.
Randomly dilated convolutions and context excitation can push ResNet-34 to state-of-the-art image classification accuracy, even on datasets like Imagenette and Imagewoof where other methods struggle.
Image classification remains a fundamental yet challenging task in computer vision, particularly when fine-grained feature extraction and background noise suppression are required simultaneously. Conventional convolutional neural networks, despite their remarkable success in hierarchical feature learning, often struggle with capturing multi-scale contextual information and are susceptible to overfitting when confronted with noisy or irrelevant image regions. In this paper, we propose RDCNet (Image Classification Network with Random Dilated Convolution), a novel architecture built upon ResNet-34 that integrates three synergistic innovations to address these limitations: (1) a Multi-Branch Random Dilated Convolution (MRDC) module that employs parallel branches with varying dilation rates combined with a stochastic masking mechanism to capture fine-grained features across multiple scales while enhancing robustness against noise and overfitting; (2) a Fine-Grained Feature Enhancement (FGFE) module embedded within MRDC that bridges global contextual information with local feature representations through adaptive pooling and bilinear interpolation, thereby amplifying sensitivity to subtle visual patterns; and (3) a Context Excitation (CE) module that leverages softmax-based spatial attention and channel recalibration to dynamically emphasize task-relevant features while suppressing background interference. Extensive experiments conducted on five benchmark datasets -- CIFAR-10, CIFAR-100, SVHN, Imagenette, and Imagewoof -- demonstrate that RDCNet consistently achieves state-of-the-art classification accuracy, outperforming the second-best competing methods by margins of 0.02\%, 1.12\%, 0.18\%, 4.73\%, and 3.56\%, respectively, thereby validating the effectiveness and generalizability of the proposed approach across diverse visual recognition scenarios.