Related papers: Partial Channel Network: Compute Fewer, Perform Be…

Convolutional operator learning is gaining attention in many signal processing and computer vision applications. Learning kernels has mostly relied on so-called patch-domain approaches that extract and store many overlapping patches across…

Despite the growing success of Convolution neural networks (CNN) in the recent past in the task of scene segmentation, the standard models lack some of the important features that might result in sub-optimal segmentation outputs. The widely…

Efficient custom pooling techniques that can aggressively trim the dimensions of a feature map and thereby reduce inference compute and memory footprint for resource-constrained computer vision applications have recently gained significant…

We introduce PointConvFormer, a novel building block for point cloud based deep network architectures. Inspired by generalization theory, PointConvFormer combines ideas from point convolution, where filter weights are only based on relative…

Standard Convolutional Neural Networks (CNNs) designed for computer vision tasks tend to have large intermediate activation maps. These require large working memory and are thus unsuitable for deployment on resource-constrained devices…

Since medical image data sets contain few samples and singular features, lesions are viewed as highly similar to other tissues. The traditional neural network has a limited ability to learn features. Even if a host of feature maps is…

Accurate segmentation of the region of interest in medical images can provide an essential pathway for devising effective treatment plans for life-threatening diseases. It is still challenging for U-Net, and its state-of-the-art variants,…

Automated segmentation of the optic cup and disk on retinal fundus images is fundamental for the automated detection / analysis of glaucoma. Traditional segmentation approaches depend heavily upon hand-crafted features and a priori…

We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We find that fine-tuning methods based on instance-discriminative contrastive learning are not as…

Traditional human vision-centric image compression methods are suboptimal for machine vision centric compression due to different visual properties and feature characteristics. To address this problem, we propose a Channel Importance-driven…

One of the practical choices for making a lightweight semantic segmentation model is to combine a depth-wise separable convolution with a dilated convolution. However, the simple combination of these two methods results in an…

Image-level weakly supervised semantic segmentation is a challenging problem that has been deeply studied in recent years. Most of advanced solutions exploit class activation map (CAM). However, CAMs can hardly serve as the object mask due…

Remarkable effectiveness of the channel or spatial attention mechanisms for producing more discernible feature representation are illustrated in various computer vision tasks. However, modeling the cross-channel relationships with channel…

This paper presents Discriminative Part Network (DP-Net), a deep architecture with strong interpretation capabilities, which exploits a pretrained Convolutional Neural Network (CNN) combined with a part-based recognition module. This system…

Fine-tuning pre-trained foundation models has gained significant popularity in various research fields. Existing methods for fine-tuning can be roughly divided into two categories, namely Parameter-Efficient Fine-Tuning and High-Performance…

Current state-of-the-art medical image segmentation methods prioritize accuracy but often at the expense of increased computational demands and larger model sizes. Applying these large-scale models to the relatively limited scale of medical…

Accurate segmentation of Pelvic Radiation Injury (PRI) from Magnetic Resonance Images (MRI) is crucial for more precise prognosis assessment and the development of personalized treatment plans. However, automated segmentation remains…

Convolution is the main building block of convolutional neural networks (CNN). We observe that an optimized CNN often has highly correlated filters as the number of channels increases with depth, reducing the expressive power of feature…

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, exceed the state-of-the-art in semantic segmentation. Our key…

Local features and contextual dependencies are crucial for 3D point cloud analysis. Many works have been devoted to designing better local convolutional kernels that exploit the contextual dependencies. However, current point convolutions…