Related papers: Split to Be Slim: An Overlooked Redundancy in Vani…
The channel redundancy in feature maps of convolutional neural networks (CNNs) results in the large consumption of memories and computational resources. In this work, we design a novel Slim Convolution (SlimConv) module to boost the…
Recent researches indicate that utilizing the frequency information of input data can enhance the performance of networks. However, the existing popular convolutional structure is not designed specifically for utilizing the frequency…
In natural images, information is conveyed at different frequencies where higher frequencies are usually encoded with fine details and lower frequencies are usually encoded with global structures. Similarly, the output feature maps of a…
Convolutional Neural Networks (CNNs) have achieved remarkable success in various computer vision tasks but rely on tremendous computational cost. To solve this problem, existing approaches either compress well-trained large-scale models or…
This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce…
Despite their strong modeling capacities, Convolutional Neural Networks (CNNs) are often scale-sensitive. For enhancing the robustness of CNNs to scale variance, multi-scale feature fusion from different layers or filters attracts great…
Convolutional Neural Networks (CNNs) have achieved state-of-the-art performance in many computer vision tasks over the years. However, this comes at the cost of heavy computation and memory intensive network designs, suggesting potential…
We propose Re-parameterized Refocusing Convolution (RefConv) as a replacement for regular convolutional layers, which is a plug-and-play module to improve the performance without any inference costs. Specifically, given a pre-trained model,…
Vision foundation models (VFMs) have demonstrated remarkable capabilities in learning universal visual representations. However, adapting these models to downstream tasks conventionally requires parameter updates, with even…
Model compression and acceleration are attracting increasing attentions due to the demand for embedded devices and mobile applications. Research on efficient convolutional neural networks (CNNs) aims at removing feature redundancy by…
Dynamic convolution achieves better performance for efficient CNNs at the cost of negligible FLOPs increase. However, the performance increase can not match the significantly expanded number of parameters, which is the main bottleneck in…
Convolutional layers are one of the basic building blocks of modern deep neural networks. One fundamental assumption is that convolutional kernels should be shared for all examples in a dataset. We propose conditionally parameterized…
Large multimodal models excel in multimodal tasks but face significant computational challenges due to excessive computation on visual tokens. Unlike token reduction methods that focus on token-level redundancy, we identify and study the…
To accelerate inference of Convolutional Neural Networks (CNNs), various techniques have been proposed to reduce computation redundancy. Converting convolutional layers into frequency domain significantly reduces the computation complexity…
3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects. In this paper, we analyze major components of existing sparse 3D CNNs and find that…
Semantic Segmentation using deep convolutional neural network pose more complex challenge for any GPU intensive task. As it has to compute million of parameters, it results to huge memory consumption. Moreover, extracting finer features and…
In this work, we tackle model efficiency by exploiting redundancy in the \textit{implicit structure} of the building blocks of convolutional neural networks. We start our analysis by introducing a general definition of Composite Kernel…
In Neural Networks, there are various methods of feature fusion. Different strategies can significantly affect the effectiveness of feature representation, consequently influencing the ability of model to extract representative and…
This work presents and analyzes three convolutional neural network (CNN) models for efficient pixelwise classification of images. When using convolutional neural networks to classify single pixels in patches of a whole image, a lot of…
As convolution has empowered many smart applications, dynamic convolution further equips it with the ability to adapt to diverse inputs. However, the static and dynamic convolutions are either layout-agnostic or computation-heavy, making it…