Related papers: Task Relevance Is Not Local Replaceability: A Two-…

Convolutional neural networks (ConvNets) are widely used in real life. People usually use ConvNets which pre-trained on a fixed number of classes. However, for different application scenarios, we usually do not need all of the classes,…

Deep neural networks (DNNs) have achieved remarkable success in object detection tasks, but their increasing complexity poses significant challenges for deployment on resource-constrained platforms. While model compression techniques such…

For semantic segmentation of remote sensing images (RSI), trade-off between representation power and location accuracy is quite important. How to get the trade-off effectively is an open question,where current approaches of utilizing very…

A challenge of channel pruning is designing efficient and effective criteria to select channels to prune. A widely used criterion is minimal performance degeneration. To accurately evaluate the truth performance degeneration requires…

Filter pruning is effective to reduce the computational costs of neural networks. Existing methods show that updating the previous pruned filter would enable large model capacity and achieve better performance. However, during the iterative…

Classification-regression prediction networks have realized impressive success in several modern deep trackers. However, there is an inherent difference between classification and regression tasks, so they have diverse even opposite demands…

Vision tasks are characterized by the properties of locality and translation invariance. The superior performance of convolutional neural networks (CNNs) on these tasks is widely attributed to the inductive bias of locality and weight…

Filter pruning has been widely used for neural network compression because of its enabled practical acceleration. To date, most of the existing filter pruning works explore the importance of filters via using intra-channel information. In…

Large-scale neural networks have demonstrated remarkable performance in different domains like vision and language processing, although at the cost of massive computation resources. As illustrated by compression literature, structural model…

The core problem of Magnetic Resonance Imaging (MRI) is the trade off between acceleration and image quality. Image reconstruction and super-resolution are two crucial techniques in Magnetic Resonance Imaging (MRI). Current methods are…

Mechanistic interpretability aims to break models into meaningful parts; verifying that two such parts implement the same computation is a prerequisite. Existing similarity measures evaluate either empirical behaviour, leaving them blind to…

Exploring the transferability between heterogeneous tasks sheds light on their intrinsic interconnections, and consequently enables knowledge transfer from one task to another so as to reduce the training effort of the latter. In this…

Existing generalization measures that aim to capture a model's simplicity based on parameter counts or norms fail to explain generalization in overparameterized deep neural networks. In this paper, we introduce a new, theoretically…

How interpretable are the features of leading vision models? The question is increasingly pressing as these models move from research benchmarks into high-stakes deployments, yet existing methods cannot answer it reliably. We close this gap…

One of the most effective methods of channel pruning is to trim on the basis of the importance of each neuron. However, measuring the importance of each neuron is an NP-hard problem. Previous works have proposed to trim by considering the…

Vision Transformer (ViT) attains state-of-the-art performance in visual recognition, and the variant, Local Vision Transformer, makes further improvements. The major component in Local Vision Transformer, local attention, performs the…

Convolutional networks are ubiquitous in deep learning. They are particularly useful for images, as they reduce the number of parameters, reduce training time, and increase accuracy. However, as a model of the brain they are seriously…

In general, image restoration involves mapping from low quality images to their high-quality counterparts. Such optimal mapping is usually non-linear and learnable by machine learning. Recently, deep convolutional neural networks have…

As wireless networks transition toward 6G, high mobility, clustered scattering, and hardware impairments increasingly challenge classical assumptions on channel sparsity, resolvability, and stationarity. In these regimes, performance…

Modern machine learning often relies on optimizing a neural network's parameters using a loss function to learn complex features. Beyond training, examining the loss function with respect to a network's parameters (i.e., as a loss…