相关论文: EfficientSAM3: Progressive Hierarchical Distillati…

Segment Anything Model (SAM) has emerged as a powerful tool for numerous vision applications. A key component that drives the impressive performance for zero-shot transfer and high versatility is a super large Transformer model trained on…

Deploying high-performing 3D medical image segmenters (e.g., nnU-Net) is often limited by memory footprint and inference latency. Compression is therefore necessary, but compact 3D encoders tend to lose fine structural cues (small lesions…

The recent development of deep learning large models in medicine shows remarkable performance in medical image analysis and diagnosis, but their large number of parameters causes memory and inference latency challenges. Knowledge…

Recently segment anything model (SAM) has shown powerful segmentation capability and has drawn great attention in computer vision fields. Massive following works have developed various applications based on the pre-trained SAM and achieved…

Segment Anything Models (SAM) achieve impressive universal segmentation performance but require massive datasets (e.g., 11M images) and rely solely on RGB inputs. Recent efficient variants reduce computation but still depend on large-scale…

Few-Shot Semantic Segmentation (FSS) focuses on segmenting novel object categories from only a handful of annotated examples. Most existing approaches rely on extensive episodic training to learn transferable representations, which is both…

In the past few years, transformers have achieved promising performances on various computer vision tasks. Unfortunately, the immense inference overhead of most existing vision transformers withholds their from being deployed on edge…

Previous Knowledge Distillation based efficient image retrieval methods employs a lightweight network as the student model for fast inference. However, the lightweight student model lacks adequate representation capacity for effective…

Segment Anything Model 2 (SAM 2) serves as a core foundation model in the field of video segmentation. Building upon the original SAM model, it introduces a memory bank mechanism and demonstrates outstanding performance in tasks such as…

SAM3D enables scalable, open-world 3D reconstruction from complex scenes, yet its deployment is hindered by prohibitive inference latency. In this work, we conduct the \textbf{first systematic investigation} into its inference dynamics,…

Segmenting 3D assets into their constituent parts is crucial for enhancing 3D understanding, facilitating model reuse, and supporting various applications such as part generation. However, current methods face limitations such as poor…

Diffusion models are a powerful generative framework, but come with expensive inference. Existing acceleration methods often compromise image quality or fail under complex conditioning when operating in an extremely low-step regime. In this…

Semantic Segmentation combines two sub-tasks: the identification of pixel-level image masks and the application of semantic labels to those masks. Recently, so-called Foundation Models have been introduced; general models trained on very…

Deep learning-based object detection has revolutionized Precision Livestock Farming (PLF), yet a critical barrier remains: high-performance Foundation Models (such as SAM 3) are too computationally intensive for edge deployment, while…

Video Object Segmentation (VOS) is foundational to numerous computer vision applications, including surveillance, autonomous driving, robotics and generative video editing. However, existing VOS models often struggle with precise mask…

The limited availability of labeled data has driven advancements in semi-supervised learning for medical image segmentation. Modern large-scale models tailored for general segmentation, such as the Segment Anything Model (SAM), have…

Deploying medical image segmentation models in routine clinical workflows is often constrained by on-premises infrastructure, where computational resources are fixed and cloud-based inference may be restricted by governance and security…

Multi-modality image fusion, particularly infrared and visible, plays a crucial role in integrating diverse modalities to enhance scene understanding. Although early research prioritized visual quality, preserving fine details and adapting…

In the context of label-efficient learning on video data, the distillation method and the structural design of the teacher-student architecture have a significant impact on knowledge distillation. However, the relationship between these…

Diffusion models excel in image generation but are computational and resource-intensive due to their reliance on iterative Markov chain processes, leading to error accumulation and limiting the effectiveness of naive compression techniques.…