Related papers: Sandwich Batch Normalization: A Drop-In Replacemen…

Heterogeneous domain adaptation (HDA) transfers knowledge across source and target domains that present heterogeneities e.g., distinct domain distributions and difference in feature type or dimension. Most previous HDA methods tackle this…

Medical image segmentation faces critical challenges in semi-supervised learning scenarios due to severe annotation scarcity requiring expert radiological knowledge, significant inter-annotator variability across different viewpoints and…

Recent advancement in generative models have demonstrated remarkable performance across various data modalities. Beyond their typical use in data synthesis, these models play a crucial role in distribution matching tasks such as latent…

We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS). BN-NAS can significantly reduce the time required by model training and evaluation in NAS. Specifically, for…

Domain generalization for semantic segmentation aims to mitigate the degradation in model performance caused by domain shifts. However, in many real-world scenarios, we are unable to access the model parameters and architectural details due…

Normalization techniques are important in different advanced neural networks and different tasks. This work investigates a novel dynamic learning-to-normalize (L2N) problem by proposing Exemplar Normalization (EN), which is able to learn…

Federated Learning (FL) is a collaborative method for training models while preserving data privacy in decentralized settings. However, FL encounters challenges related to data heterogeneity, which can result in performance degradation. In…

The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering. Segment-Anything(SAM), among others, is the…

Blending multiple convolutional kernels is proved advantageous in neural architecture design. However, current two-stage neural architecture search methods are mainly limited to single-path search spaces. How to efficiently search models of…

Single image generative models perform synthesis and manipulation tasks by capturing the distribution of patches within a single image. The classical (pre Deep Learning) prevailing approaches for these tasks are based on an optimization…

Deep Neural Network (DNN) based super-resolution algorithms have greatly improved the quality of the generated images. However, these algorithms often yield significant artifacts when dealing with real-world super-resolution problems due to…

Various normalization layers have been proposed to help the training of neural networks. Group Normalization (GN) is one of the effective and attractive studies that achieved significant performances in the visual recognition task. Despite…

Environment perception in autonomous driving vehicles often heavily relies on deep neural networks (DNNs), which are subject to domain shifts, leading to a significantly decreased performance during DNN deployment. Usually, this problem is…

Regularization techniques help prevent overfitting and therefore improve the ability of convolutional neural networks (CNNs) to generalize. One reason for overfitting is the complex co-adaptations among different parts of the network, which…

Despite transformers being considered as the new standard in computer vision, convolutional neural networks (CNNs) still outperform them in low-data regimes. Nonetheless, CNNs often make decisions based on narrow, specific regions of input…

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…

Extensive researches have applied deep neural networks (DNNs) in class incremental learning (Class-IL). As building blocks of DNNs, batch normalization (BN) standardizes intermediate feature maps and has been widely validated to improve…

Batch normalization (BN) has become a de facto standard for training deep convolutional networks. However, BN accounts for a significant fraction of training run-time and is difficult to accelerate, since it is a memory-bandwidth bounded…

Face anti-spoofing (FAS) plays a critical role in securing face recognition systems from different presentation attacks. Previous works leverage auxiliary pixel-level supervision and domain generalization approaches to address unseen spoof…

While post-training quantization receives popularity mostly due to its evasion in accessing the original complete training dataset, its poor performance also stems from scarce images. To alleviate this limitation, in this paper, we leverage…