Related papers: Dynamic Region-Aware Convolution
3D spatial information is known to be beneficial to the semantic segmentation task. Most existing methods take 3D spatial data as an additional input, leading to a two-stream segmentation network that processes RGB and 3D spatial…
Most image denoising networks apply a single set of static convolutional kernels across the entire input image. This is sub-optimal for natural images, as they often consist of heterogeneous visual patterns. Dynamic convolution tries to…
Group convolution, which divides the channels of ConvNets into groups, has achieved impressive improvement over the regular convolution operation. However, existing models, eg. ResNeXt, still suffers from the sub-optimal performance due to…
Convolution as inner product has been the founding basis of convolutional neural networks (CNNs) and the key to end-to-end visual representation learning. Benefiting from deeper architectures, recent CNNs have demonstrated increasingly…
Deep neural networks are playing an important role in state-of-the-art visual recognition. To represent high-level visual concepts, modern networks are equipped with large convolutional layers, which use a large number of filters and…
Convolutional Neural Network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only operate convolution on…
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…
We propose contextual convolution (CoConv) for visual recognition. CoConv is a direct replacement of the standard convolution, which is the core component of convolutional neural networks. CoConv is implicitly equipped with the capability…
The spatial attention mechanism has been widely used to improve object detection performance. However, its operation is currently limited to static convolutions lacking content-adaptive features. This paper innovatively approaches from the…
Deep convolutional networks have attracted great attention in image restoration and enhancement. Generally, restoration quality has been improved by building more and more convolutional block. However, these methods mostly learn a specific…
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,…
We present a new convolutional neural network, called Multi Voxel-Point Neurons Convolution (MVPConv), for fast and accurate 3D deep learning. The previous works adopt either individual point-based features or local-neighboring voxel-based…
High-dimensional generative models have many applications including image compression, multimedia generation, anomaly detection and data completion. State-of-the-art estimators for natural images are autoregressive, decomposing the joint…
Recently, convolutional neural networks (CNNs) have been widely used in sound event detection (SED). However, traditional convolution is deficient in learning time-frequency domain representation of different sound events. To address this…
Convolutional Neural Networks (CNNs) have recently been shown to excel at performing visual place recognition under changing appearance and viewpoint. Previously, place recognition has been improved by intelligently selecting relevant…
Learned image compression (LIC) has recently made significant progress, surpassing traditional methods. However, most LIC approaches operate mainly in the spatial domain and lack mechanisms for reducing frequency-domain correlations. To…
Convolutional Neural Networks (CNNs) have exhibited their great power in a variety of vision tasks. However, the lack of transform-invariant property limits their further applications in complicated real-world scenarios. In this work, we…
Unlike images which are represented in regular dense grids, 3D point clouds are irregular and unordered, hence applying convolution on them can be difficult. In this paper, we extend the dynamic filter to a new convolution operation, named…
Transformers have captured growing attention in computer vision, thanks to its large capacity and global processing capabilities. However, transformers are data hungry, and their ability to generalize is constrained compared to…
The performance of local feature descriptors degrades in the presence of large rotation variations. To address this issue, we present an efficient approach to learning rotation invariant descriptors. Specifically, we propose Rotated Kernel…