Related papers: Tarot-SAM3: Training-free SAM3 for Any Referring E…
We study fine-grained referring image segmentation via a decoupled reason-then-segment pipeline. A vision-language model (VLM) receives an image and a natural-language query, reasons about the scene, and emits structured spatial prompts: a…
Referring image segmentation aims to segment the objects referred by a natural language expression. Previous methods usually focus on designing an implicit and recurrent feature interaction mechanism to fuse the visual-linguistic features…
3D Referring Expression Segmentation (3D-RES) is dedicated to segmenting a specific instance within a 3D space based on a natural language description. However, current approaches are limited to segmenting a single target, restricting the…
Referring Remote Sensing Image Segmentation (RRSIS) aims to segment instances in remote sensing images according to referring expressions. Unlike Referring Image Segmentation on general images, acquiring high-quality referring expressions…
Segment Anything Model (SAM), a prompt-driven foundation model for natural image segmentation, has demonstrated impressive zero-shot performance. However, SAM does not work when directly applied to medical image segmentation, since SAM…
Leveraging the extensive training data from SA-1B, the Segment Anything Model (SAM) demonstrates remarkable generalization and zero-shot capabilities. However, as a category-agnostic instance segmentation method, SAM heavily relies on prior…
Reasoning Video Object Segmentation (ReasonVOS) is a challenging task that requires stable object segmentation across video sequences using implicit and complex textual inputs. Previous methods fine-tune Multimodal Large Language Models…
Generalized Referring Expression Segmentation (GRES) extends the scope of classic RES to refer to multiple objects in one expression or identify the empty targets absent in the image. GRES poses challenges in modeling the complex spatial…
Existing face parsing methods usually misclassify occlusions as facial components. This is because occlusion is a high-level concept, it does not refer to a concrete category of object. Thus, constructing a real-world face dataset covering…
The primary challenge of cross-domain few-shot segmentation (CD-FSS) is the domain disparity between the training and inference phases, which can exist in either the input data or the target classes. Previous models struggle to learn…
In this paper, we study a challenging task of zero-shot referring image segmentation. This task aims to identify the instance mask that is most related to a referring expression without training on pixel-level annotations. Previous research…
One-shot medical image segmentation (MIS) is crucial for medical analysis due to the burden of medical experts on manual annotation. The recent emergence of the segment anything model (SAM) has demonstrated remarkable adaptation in MIS but…
This report presents our winning solution to the 5th PVUW MeViS-Text Challenge. The track studies referring video object segmentation under motion-centric language expressions, where the model must jointly understand appearance, temporal…
In semantic segmentation, accurate prediction masks are crucial for downstream tasks such as medical image analysis and image editing. Due to the lack of annotated data, few-shot semantic segmentation (FSS) performs poorly in predicting…
Referring image segmentation (RIS) is a fundamental vision-language task that intends to segment a desired object from an image based on a given natural language expression. Due to the essentially distinct data properties between image and…
In light of the diminishing returns of traditional methods for enhancing transmission rates, the domain of semantic communication presents promising new frontiers. Focusing on image transmission, this paper explores the application of…
Although the Segment Anything Model (SAM) is highly effective in natural image segmentation, it requires dependencies on prompts, which limits its applicability to medical imaging where manual prompts are often unavailable. Existing efforts…
3D referring segmentation is an emerging and challenging vision-language task that aims to segment the object described by a natural language expression in a point cloud scene. The key challenge behind this task is vision-language feature…
In-context segmentation (ICS) aims to segment arbitrary concepts, e.g., objects, parts, or personalized instances, given one annotated visual examples. Existing work relies on (i) fine-tuning vision foundation models (VFMs), which improves…
Reasoning segmentation is an emerging vision-language task that requires reasoning over intricate text queries to precisely segment objects. However, existing methods typically suffer from overthinking, generating verbose reasoning chains…