Related papers: SDPose: Tokenized Pose Estimation via Circulation-…

Recent approaches have shown promises distilling diffusion models into efficient one-step generators. Among them, Distribution Matching Distillation (DMD) produces one-step generators that match their teacher in distribution, without…

Dataset distillation has emerged as an effective strategy, significantly reducing training costs and facilitating more efficient model deployment. Recent advances have leveraged generative models to distill datasets by capturing the…

Transformer-based trackers have achieved strong accuracy on the standard benchmarks. However, their efficiency remains an obstacle to practical deployment on both GPU and CPU platforms. In this paper, to overcome this issue, we propose a…

Sparse autoencoders (SAEs) aim to disentangle model activations into monosemantic, human-interpretable features. In practice, learned features are often redundant and vary across training runs and sparsity levels, which makes…

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…

Self-supervised learning (SSL) has made remarkable progress in visual representation learning. Some studies combine SSL with knowledge distillation (SSL-KD) to boost the representation learning performance of small models. In this study, we…

Model distillation enables the transfer of knowledge from large-scale models to compact student models, facilitating deployment in resource-constrained environments. However, conventional distillation approaches often suffer from…

Dataset distillation compresses the original data into compact synthetic datasets, reducing training time and storage while retaining model performance, enabling deployment under limited resources. Although recent decoupling-based…

Tokenizers are a key component of state-of-the-art generative image models, extracting the most important features from the signal while reducing data dimension and redundancy. Most current tokenizers are based on KL-regularized variational…

Self-supervised foundation models have shown great potential in computer vision thanks to the pre-training paradigm of masked autoencoding. Scale is a primary factor influencing the performance of these foundation models. However, these…

We present MovePose, an optimized lightweight convolutional neural network designed specifically for real-time body pose estimation on CPU-based mobile devices. The current solutions do not provide satisfactory accuracy and speed for human…

The 3D Human Pose Estimation (3D HPE) task uses 2D images or videos to predict human joint coordinates in 3D space. Despite recent advancements in deep learning-based methods, they mostly ignore the capability of coupling accessible texts…

Dataset distillation (DD) aims to compress large-scale datasets into compact synthetic sets while preserving training efficacy. However, existing studies mainly focus on image classification, leaving dense prediction tasks such as semantic…

Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) have led to significant progress in 2D body pose estimation. However, achieving a good balance between accuracy, efficiency, and robustness remains a challenge. For…

Medical image annotation is constrained by privacy concerns and labor-intensive labeling, significantly limiting the performance and generalization of segmentation models. While mask-controllable diffusion models excel in synthesis, they…

The application of diffusion models in 3D LiDAR scene completion is limited due to diffusion's slow sampling speed. Score distillation accelerates diffusion sampling but with performance degradation, while post-training with direct policy…

Self-distillation has emerged as a promising technique for improving model performance in modern machine learning systems. We develop the statistical foundations of self-distillation in spiked covariance models, by introducing and analyzing…

Latest diffusion models have shown promising results in category-level 6D object pose estimation by modeling the conditional pose distribution with depth image input. The existing methods, however, suffer from slow convergence during…

Diffusion-based image compression has demonstrated impressive perceptual performance. However, it suffers from two critical drawbacks: (1) excessive decoding latency due to multi-step sampling, and (2) poor fidelity resulting from…

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…