Scale-invariant object detection by adaptive convolution with unified global-local context

Amrita Singh, Snehasis Mukherjee

Abstract: Dense features are important for detecting differnet scale objects in images. Unfortunately, despite the remarkable efficacy of the CNN models in multi-scale object detection, CNN models often fail to detect different scale objects in images due to using similar type of CNN features. Atrous convolution addresses this issue by applying sparse kernels. However, sparse kernels often can lose the multi-scale detection efficacy of the CNN model. In this paper, we propose an object detection model using a Switchable Atrous Convolutional Network (SAC-Net) based on the efficientDet model.A fixed atrous rate limits the performance of the CNN models in the convolutional layers. To overcome this limitation, we introduce a switchable mechanism that allows dynamically adjusting the atrous rate during the forward pass. The proposed SAC-Net encapsulates the benefits of both low-level and high-level features to achieve improved performance on multi-scale object detection tasks, without losing the dense features. Further, we apply a depth-wise switchable atrous rate to the proposed network, to improve the scale-invariant features. Finally, we apply the global context to the proposed model. Our extensive experiments on benchmark datasets demonstrate that the proposed SAC-Net outperforms the state-of-the-art models by a significant margin in terms of accuracy. The code will be released after acceptance.

External IDs:dblp:journals/evs/SinghM25