Related papers: Fine-grained Data Distribution Alignment for Post-…

Deep convolutional neural network models pre-trained for the ImageNet classification task have been successfully adopted to tasks in other domains, such as texture description and object proposal generation, but these tasks require…

Consistency regularization is one of the most widely-used techniques for semi-supervised learning (SSL). Generally, the aim is to train a model that is invariant to various data augmentations. In this paper, we revisit this idea and find…

In many applications of deep learning, particularly those in image restoration, it is either very difficult, prohibitively expensive, or outright impossible to obtain paired training data precisely as in the real world. In such cases, one…

Federated learning (FL) has emerged as a promising paradigm for privacy-preserving distributed machine learning, but faces challenges with heterogeneous data distributions across clients. This paper presents FedSat, a novel FL approach…

Quantization has emerged as one of the most prevalent approaches to compress and accelerate neural networks. Recently, data-free quantization has been widely studied as a practical and promising solution. It synthesizes data for calibrating…

It is commonly believed that gradient compression in federated learning (FL) enjoys significant improvement in communication efficiency with negligible performance degradation. In this paper, we find that gradient compression induces…

Deep Neural Networks (DNNs) are computationally and memory intensive, which makes their hardware implementation a challenging task especially for resource constrained devices such as IoT nodes. To address this challenge, this paper…

Handling distribution shifts from training data, known as out-of-distribution (OOD) generalization, poses a significant challenge in the field of machine learning. While a pre-trained vision-language model like CLIP has demonstrated…

Given a ground-level query image and a geo-referenced aerial image that covers the query's local surroundings, fine-grained cross-view localization aims to estimate the location of the ground camera inside the aerial image. Recent works…

The post-training quantization (PTQ) challenge of bringing quantized neural net accuracy close to original has drawn much attention driven by industry demand. Many of the methods emphasize optimization of a specific degree-of-freedom (DoF),…

The complexity of deep neural network algorithms for hardware implementation can be much lowered by optimizing the word-length of weights and signals. Direct quantization of floating-point weights, however, does not show good performance…

Low-bit quantization of network weights and activations can drastically reduce the memory footprint, complexity, energy consumption and latency of Deep Neural Networks (DNNs). However, low-bit quantization can also cause a considerable drop…

The emerging paradigm of federated learning (FL) strives to enable collaborative training of deep models on the network edge without centrally aggregating raw data and hence improving data privacy. In most cases, the assumption of…

Although quantization has emerged as a promising approach to reducing computational complexity across various high-level vision tasks, it inevitably leads to accuracy loss in image super-resolution (SR) networks. This is due to the…

Since the introduction of modern deep learning methods for object pose estimation, test accuracy and efficiency has increased significantly. For training, however, large amounts of annotated training data are required for good performance.…

Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendous demand for intelligent edge devices featuring on-site learning, while the practical realization of such systems remains a challenge due to the limited resources…

Federated learning (FL) has shown success in collaboratively training a model among decentralized data resources without directly sharing privacy-sensitive training data. Despite recent advances, non-IID (non-independent and identically…

While fine-tuning is a de facto standard method for training deep neural networks, it still suffers from overfitting when using small target datasets. Previous methods improve fine-tuning performance by maintaining knowledge of the source…

Recently, transformer has achieved remarkable performance on a variety of computer vision applications. Compared with mainstream convolutional neural networks, vision transformers are often of sophisticated architectures for extracting…

Recent image generative models typically capture the image distribution in a pre-constructed latent space, relying on a frozen image tokenizer. However, there exists a significant discrepancy between the reconstruction and generation…