Related papers: Fast-HaMeR: Boosting Hand Mesh Reconstruction usin…
Reconstructing 3D hand mesh robustly from a single image is very challenging, due to the lack of diversity in existing real-world datasets. While data synthesis helps relieve the issue, the syn-to-real gap still hinders its usage. In this…
Knowledge distillation has been shown to be a powerful model compression approach to facilitate the deployment of pre-trained language models in practice. This paper focuses on task-agnostic distillation. It produces a compact pre-trained…
The concept of compressing deep Convolutional Neural Networks (CNNs) is essential to use limited computation, power, and memory resources on embedded devices. However, existing methods achieve this objective at the cost of a drop in…
Knowledge distillation has been applied to various tasks successfully. The current distillation algorithm usually improves students' performance by imitating the output of the teacher. This paper shows that teachers can also improve…
Vision Transformers (ViTs) have achieved significant advancement in computer vision tasks due to their powerful modeling capacity. However, their performance notably degrades when trained with insufficient data due to lack of inherent…
Accurate 3D medical image segmentation is vital for diagnosis and treatment planning, but state-of-the-art models are often too large for clinics with limited computing resources. Lightweight architectures typically suffer significant…
Transformer-based architectures have become the de-facto standard models for diverse vision tasks owing to their superior performance. As the size of the models continues to scale up, model distillation becomes extremely important in…
Recent advances in model compression have provided procedures for compressing large neural networks to a fraction of their original size while retaining most if not all of their accuracy. However, all of these approaches rely on access to…
In instance-level detection tasks (e.g., object detection), reducing input resolution is an easy option to improve runtime efficiency. However, this option traditionally hurts the detection performance much. This paper focuses on boosting…
Deep neural network architectures have attained remarkable improvements in scene understanding tasks. Utilizing an efficient model is one of the most important constraints for limited-resource devices. Recently, several compression methods…
Despite substantial progress in 3D object detection, advanced 3D detectors often suffer from heavy computation overheads. To this end, we explore the potential of knowledge distillation (KD) for developing efficient 3D object detectors,…
The model reduction problem that eases the computation costs and latency of complex deep learning architectures has received an increasing number of investigations owing to its importance in model deployment. One promising method is…
Real-time 6D object pose estimation is essential for many real-world applications, such as robotic grasping and augmented reality. To achieve an accurate object pose estimation from RGB images in real-time, we propose an effective and…
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model. Previous KD methods typically train a student by minimizing a task-related loss and…
Knowledge distillation (KD) in transformers often faces challenges due to misalignment in the number of attention heads between teacher and student models. Existing methods either require identical head counts or introduce projectors to…
Finding a person across a camera network plays an important role in video surveillance. For a real-world person re-identification application, in order to guarantee an optimal time response, it is crucial to find the balance between…
The development of computer vision solutions for gigapixel images in digital pathology is hampered by significant computational limitations due to the large size of whole slide images. In particular, digitizing biopsies at high resolutions…
High Dynamic Range (HDR) video reconstruction aims to recover fine brightness, color, and details from Low Dynamic Range (LDR) videos. However, existing methods often suffer from color inaccuracies and temporal inconsistencies. To address…
In recent years, numerous real-time stereo matching methods have been introduced, but they often lack accuracy. These methods attempt to improve accuracy by introducing new modules or integrating traditional methods. However, the…
Facial forgery detection is a crucial but extremely challenging topic, with the fast development of forgery techniques making the synthetic artefact highly indistinguishable. Prior works show that by mining both spatial and frequency…