Related papers: AI-KD: Towards Alignment Invariant Face Image Qual…

Existing full-reference image quality assessment (FR-IQA) methods achieve high-precision evaluation by analysing feature differences between reference and distorted images. However, their performance is constrained by the quality of the…

In recent years, image generation technology has rapidly advanced, resulting in the creation of a vast array of AI-generated images (AIGIs). However, the quality of these AIGIs is highly inconsistent, with low-quality AIGIs severely…

Face recognition networks generally demonstrate bias with respect to sensitive attributes like gender, skintone etc. For gender and skintone, we observe that the regions of the face that a network attends to vary by the category of an…

Knowledge distillation (KD) is a promising yet challenging model compression technique that transfers rich learning representations from a well-performing but cumbersome teacher model to a compact student model. Previous methods for image…

We propose Cross-Attention-based Non-local Knowledge Distillation (CanKD), a novel feature-based knowledge distillation framework that leverages cross-attention mechanisms to enhance the knowledge transfer process. Unlike traditional…

Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size.…

Knowledge Distillation (KD), a learning manner with a larger teacher network guiding a smaller student network, transfers dark knowledge from the teacher to the student via logits or intermediate features, with the aim of producing a…

The goal of full-reference image quality assessment (FR-IQA) is to predict the quality of an image as perceived by human observers with using its pristine, reference counterpart. In this study, we explore a novel, combined approach which…

Efficient object detection methods have recently received great attention in remote sensing. Although deep convolutional networks often have excellent detection accuracy, their deployment on resource-limited edge devices is difficult.…

Compact and efficient 6DoF object pose estimation is crucial in applications such as robotics, augmented reality, and space autonomous navigation systems, where lightweight models are critical for real-time accurate performance. This paper…

With the rapid advancements in Artificial Intelligence Generated Image (AGI) technology, the accurate assessment of their quality has become an increasingly vital requirement. Prevailing methods typically rely on cross-modal models like…

In recent years, deep neural networks have achieved remarkable accuracy in computer vision tasks. With inference time being a crucial factor, particularly in dense prediction tasks such as semantic segmentation, knowledge distillation has…

BIQA (Blind Image Quality Assessment) is an important field of study that evaluates images automatically. Although significant progress has been made, blind image quality assessment remains a difficult task since images vary in content and…

Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data. Existing methods commonly avoid relying on private data by…

Autoregressive large language models (LLMs) have achieved remarkable improvement across many tasks but incur high computational and memory costs. Knowledge distillation (KD) mitigates this issue by transferring knowledge from a large…

Knowledge distillation (KD) exploits a large well-trained model (i.e., teacher) to train a small student model on the same dataset for the same task. Treating teacher features as knowledge, prevailing methods of knowledge distillation train…

In practical applications of human pose estimation, low-resolution inputs frequently occur, and existing state-of-the-art models perform poorly with low-resolution images. This work focuses on boosting the performance of low-resolution…

In this study, we introduce a feature knowledge distillation framework to improve low-resolution (LR) face recognition performance using knowledge obtained from high-resolution (HR) images. The proposed framework transfers informative…

Knowledge distillation aims to transfer knowledge to the student model by utilizing the predictions/features of the teacher model, and feature-based distillation has recently shown its superiority over logit-based distillation. However, due…

Millions of cameras at edge are being deployed to power a variety of different deep learning applications. However, the frames captured by these cameras are not always pristine - they can be distorted due to lighting issues, sensor noise,…