Related papers: Split to Be Slim: An Overlooked Redundancy in Vani…
The high demand for computational and storage resources severely impede the deployment of deep convolutional neural networks (CNNs) in limited-resource devices. Recent CNN architectures have proposed reduced complexity versions (e.g.…
Detecting slender, overlapping structures remains a challenge in computational microscopy. While recent coordinate-based approaches improve detection, they often produce less accurate splines than pixel-based methods. We introduce a…
We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels. The proposed HetConv (Heterogeneous Kernel-Based Convolution) reduces the computation (FLOPs) and the number of parameters as…
This paper proposes SConvTransform, a Transform dialect extension that provides operations for optimizing 2D convolutions in MLIR. Its main operation, SConvOp, lowers Linalg convolutions into tiled and packed generic operations through a…
The sophisticated structure of Convolutional Neural Network (CNN) allows for outstanding performance, but at the cost of intensive computation. As significant redundancies inevitably present in such a structure, many works have been…
Sparse support vector machine (SVM) is a popular classification technique that can simultaneously learn a small set of the most interpretable features and identify the support vectors. It has achieved great successes in many real-world…
Semantic instance segmentation remains a challenging task. In this work we propose to tackle the problem with a discriminative loss function, operating at the pixel level, that encourages a convolutional network to produce a representation…
Graph convolution (GConv) is a widely used technique that has been demonstrated to be extremely effective for graph learning applications, most notably node categorization. On the other hand, many GConv-based models do not quantify the…
The redundant features existing in high dimensional datasets always affect the performance of learning and mining algorithms. How to detect and remove them is an important research topic in machine learning and data mining research. In this…
Despite the powerful feature extraction capability of Convolutional Neural Networks, there are still some challenges in saliency detection. In this paper, we focus on two aspects of challenges: i) Since salient objects appear in various…
We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks. These models deliver impressive accuracy but each image evaluation requires millions of floating point…
In recent years, semantic segmentation has flourished in various applications. However, the high computational cost remains a significant challenge that hinders its further adoption. The filter pruning method for structured network slimming…
We tackle the problem of using 3D information in convolutional neural networks for down-stream recognition tasks. Using depth as an additional channel alongside the RGB input has the scale variance problem present in image convolution based…
Convolutional neural network (CNN) pruning has become one of the most successful network compression approaches in recent years. Existing works on network pruning usually focus on removing the least important filters in the network to…
Convolution is one of the most computationally intensive operations that must be performed for machine-learning model inference. A traditional approach to compute convolutions is known as the Im2Col + BLAS method. This paper proposes SConv:…
To compress deep convolutional neural networks (CNNs) with large memory footprint and long inference time, this paper proposes a novel pruning criterion using layer-wised Ln-norm of feature maps. Different from existing pruning criteria,…
Traditional convolutional layers extract features from patches of data by applying a non-linearity on an affine function of the input. We propose a model that enhances this feature extraction process for the case of sequential data, by…
We propose a method for high-performance semantic image segmentation (or semantic pixel labelling) based on very deep residual networks, which achieves the state-of-the-art performance. A few design factors are carefully considered to this…
Feed-forward 3D foundation models face a key challenge: the quadratic computational cost introduced by global attention, which severely limits scalability as input length increases. Concurrent acceleration methods, such as token merging,…
Group convolutional neural networks (G-CNNs) have been shown to increase parameter efficiency and model accuracy by incorporating geometric inductive biases. In this work, we investigate the properties of representations learned by regular…