Related papers: Efficient-SAM2: Accelerating SAM2 with Object-Awar…

The recent Segment Anything Models (SAMs) have emerged as foundational visual models for general interactive segmentation. Despite demonstrating robust generalization abilities, they still suffer performance degradations in scenarios…

Few-shot segmentation aims to segment unseen object categories from just a handful of annotated examples. This requires mechanisms that can both identify semantically related objects across images and accurately produce segmentation masks.…

In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which limits their practical applications. Furthermore, with hardware advancements, a wide range…

Previous methods based on 3DCNN, convLSTM, or optical flow have achieved great success in video salient object detection (VSOD). However, they still suffer from high computational costs or poor quality of the generated saliency maps. To…

Despite significant advances in deep learning for image and video segmentation, existing models continue to face challenges in cross-domain adaptability and generalization. Image and video segmentation are fundamental tasks in computer…

Research has focused on Multi-Modal Semantic Segmentation (MMSS), where pixel-wise predictions are derived from multiple visual modalities captured by diverse sensors. Recently, the large vision model, Segment Anything Model 2 (SAM2), has…

Deep neural networks often suffer from poor generalization caused by complex and non-convex loss landscapes. One of the popular solutions is Sharpness-Aware Minimization (SAM), which smooths the loss landscape via minimizing the maximized…

Interactive video segmentation models such as SAM2 have demonstrated strong generalization across diverse visual domains. However, under weak user supervision, for example, when sparse point prompts are provided on a single frame, their…

Recent studies have highlighted the potential of adapting the Segment Anything Model (SAM) for various downstream tasks. However, constructing a more powerful and generalizable encoder to further enhance performance remains an open…

Surgical video segmentation is crucial for computer-assisted surgery, enabling precise localization and tracking of instruments and tissues. Interactive Video Object Segmentation (iVOS) models such as Segment Anything Model 2 (SAM2) provide…

Referring Video Object Segmentation (RVOS) relies on natural language expressions to segment an object in a video clip. Existing methods restrict reasoning either to independent short clips, losing global context, or process the entire…

Few-Shot Segmentation (FSS) aims to learn class-agnostic segmentation on few classes to segment arbitrary classes, but at the risk of overfitting. To address this, some methods use the well-learned knowledge of foundation models (e.g., SAM)…

High-resolution images enable neural networks to learn richer visual representations. However, this improved performance comes at the cost of growing computational complexity, hindering their usage in latency-sensitive applications. As not…

We present EfficientViT-SAM, a new family of accelerated segment anything models. We retain SAM's lightweight prompt encoder and mask decoder while replacing the heavy image encoder with EfficientViT. For the training, we begin with the…

This paper focuses on the problem of visual saliency prediction, predicting regions of an image that tend to attract human visual attention, under a constrained computational budget. We modify and test various recent efficient convolutional…

Visual AutoRegressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction paradigm. However, mainstream VAR paradigms attend to all tokens across historical scales at each autoregressive step. As the…

With the rapid development of society and continuous advances in science and technology, the food industry increasingly demands higher production quality and efficiency. Food image classification plays a vital role in enabling automated…

Visual Object Tracking (VOT) is widely used in applications like autonomous driving to continuously track targets in videos. Existing methods can be roughly categorized into template matching and autoregressive methods, where the former…

The reliance on large labeled datasets presents a significant challenge in medical image segmentation. Few-shot learning offers a potential solution, but existing methods often still require substantial training data. This paper proposes a…

The Segment Anything Model (SAM) is a powerful vision foundation model that is revolutionizing the traditional paradigm of segmentation. Despite this, a reliance on prompting each frame and large computational cost limit its usage in…