Related papers: VQ-Seg: Vector-Quantized Token Perturbation for Se…

The Segment Anything Model (SAM) is a popular vision foundation model; however, its high computational and memory demands make deployment on resource-constrained devices challenging. While Post-Training Quantization (PTQ) is a practical…

Deep Convolutional Neural Networks have proven effective in solving the task of semantic segmentation. However, their efficiency heavily relies on the pixel-level annotations that are expensive to get and often require domain expertise,…

In theory, vector quantization (VQ) is always better than scalar quantization (SQ) in terms of rate-distortion (R-D) performance. Recent state-of-the-art methods for neural image compression are mainly based on nonlinear transform coding…

Deep convolutional neural networks (CNNs) have become an essential tool in the medical imaging-based computer-aided diagnostic pipeline. However, training accurate and reliable CNNs requires large fine-grain annotated datasets. To alleviate…

Due to the lack of quality annotation in medical imaging community, semi-supervised learning methods are highly valued in image semantic segmentation tasks. In this paper, an advanced consistency-aware pseudo-label-based self-ensembling…

Medical image segmentation methods are generally designed as fully-supervised to guarantee model performance, which require a significant amount of expert annotated samples that are high-cost and laborious. Semi-supervised image…

Biomedical image segmentation plays a significant role in computer-aided diagnosis. However, existing CNN based methods rely heavily on massive manual annotations, which are very expensive and require huge human resources. In this work, we…

Recently, video diffusion models (VDMs) have garnered significant attention due to their notable advancements in generating coherent and realistic video content. However, processing multiple frame features concurrently, coupled with the…

One of the challenges in developing deep learning algorithms for medical image segmentation is the scarcity of annotated training data. To overcome this limitation, data augmentation and semi-supervised learning (SSL) methods have been…

Supervised deep learning for semantic segmentation has achieved excellent results in accurately identifying anatomical and pathological structures in medical images. However, it often requires large annotated training datasets, which limits…

Breast cancer remains the leading cause of cancer-related mortality among women worldwide, necessitating the meticulous examination of mammograms by radiologists to characterize abnormal lesions. This manual process demands high accuracy…

Vector Quantization (VQ) techniques face significant challenges in codebook utilization, limiting reconstruction fidelity in image modeling. We introduce a Dual Codebook mechanism that effectively addresses this limitation by partitioning…

Molecular representation learning has become a central approach in AI-driven drug discovery, yet existing molecular tokenizations such as SMILES remain largely syntactic and do not naturally align with chemically meaningful substructures.…

Visual tokenizers are fundamental to image generation. They convert visual data into discrete tokens, enabling transformer-based models to excel at image generation. Despite their success, VQ-based tokenizers like VQGAN face significant…

Text-to-image diffusion models have emerged as a powerful framework for high-quality image generation given textual prompts. Their success has driven the rapid development of production-grade diffusion models that consistently increase in…

The performance of supervised deep learning methods for medical image segmentation is often limited by the scarcity of labeled data. As a promising research direction, semi-supervised learning addresses this dilemma by leveraging unlabeled…

The disparity in healthcare personnel expertise and medical resources across different regions of the world is a pressing social issue. Artificial intelligence technology offers new opportunities to alleviate this issue. Segment Anything…

Segment Anything Model (SAM) exhibits remarkable zero-shot segmentation capability; however, its prohibitive computational costs make edge deployment challenging. Although post-training quantization (PTQ) offers a promising compression…

Vector quantization (VQ) is a key component in discrete tokenizers for image generation, but its training is often unstable due to straight-through estimation bias, one-step-behind updates, and sparse codebook gradients, which lead to…

Mixture-of-Experts(MoE) Vision-Language Models (VLMs) offer remarkable performance but incur prohibitive memory and computational costs, making compression essential. Post-Training Quantization (PTQ) is an effective training-free technique…