Related papers: INSID3: Training-Free In-Context Segmentation with…
Semi-supervised learning (SSL) has emerged as a critical paradigm for medical image segmentation, mitigating the immense cost of dense annotations. However, prevailing SSL frameworks are fundamentally "inward-looking", recycling information…
When trained at a sufficient scale, self-supervised learning has exhibited a notable ability to solve a wide range of visual or language understanding tasks. In this paper, we investigate simple, yet effective approaches for adapting the…
In recent years, instance segmentation has garnered significant attention across various applications. However, training a fully-supervised instance segmentation model requires costly both instance-level and pixel-level annotations. In…
Vision foundation models (VFMs) trained on large-scale image datasets provide high-quality features that have significantly advanced 2D visual recognition. However, their potential in 3D scene segmentation remains largely untapped, despite…
Instance segmentation is a challenging task aiming at classifying and segmenting all object instances of specific classes. While two-stage box-based methods achieve top performances in the image domain, they cannot easily extend their…
Service robots operating in unstructured environments must effectively recognize and segment unknown objects to enhance their functionality. Traditional supervised learningbased segmentation techniques require extensive annotated datasets,…
To ease the difficulty of acquiring annotation labels in 3D data, a common method is using unsupervised and open-vocabulary semantic segmentation, which leverage 2D CLIP semantic knowledge. In this paper, unlike previous research that…
Recent deep learning models achieve impressive results on 3D scene analysis tasks by operating directly on unstructured point clouds. A lot of progress was made in the field of object classification and semantic segmentation. However, the…
This paper presents the first study on adapting the visual in-context learning (V-ICL) paradigm to optical character recognition tasks, specifically focusing on text removal and segmentation. Most existing V-ICL generalists employ a…
Fully supervised semantic segmentation learns from dense masks, which requires heavy annotation cost for closed set. In this paper, we use natural language as supervision without any pixel-level annotation for open world segmentation. We…
Adapting foundation models to medical segmentation typically requires either backbone fine-tuning or high-capacity task-specific decoders, both of which are difficult to fit reliably when annotations are scarce. We show that frozen DINOv3…
This paper evaluates DINOv3, a recent large-scale self-supervised vision backbone, for visuomotor diffusion policy learning in robotic manipulation. We investigate whether a purely self-supervised encoder can match or surpass conventional…
Focusing on only semantic instances that only salient in a scene gains more benefits for robot navigation and self-driving cars than looking at all objects in the whole scene. This paper pushes the envelope on salient regions in a video to…
2D visual foundation models, such as DINOv3, a self-supervised model trained on large-scale natural images, have demonstrated strong zero-shot generalization, capturing both rich global context and fine-grained structural cues. However, an…
Existing semantic segmentation approaches either aim to improve the object's inner consistency by modeling the global context, or refine objects detail along their boundaries by multi-scale feature fusion. In this paper, a new paradigm for…
Monocular depth estimation is fundamental for 3D scene understanding and downstream applications. However, even under the supervised setup, it is still challenging and ill-posed due to the lack of full geometric constraints. Although a…
We tackle the problem of object-centric learning on point clouds, which is crucial for high-level relational reasoning and scalable machine intelligence. In particular, we introduce a framework, SPAIR3D, to factorize a 3D point cloud into a…
Despite the significant advancements in general image segmentation achieved by large-scale pre-trained foundation models (such as Meta's Segment Any-thing Model (SAM) series and DINOv2), their performance in specialized fields remains…
The Segment Anything Model (SAM) was originally designed for label-agnostic mask generation. Does this model also possess inherent semantic understanding, of value to broader visual tasks? In this work we follow a multi-staged approach…
Vision foundation models can perform generalized object classification in zero-shot mode, and face/person recognition when they are fine-tuned. However, fine-tuned models suffer from catastrophic forgetting. We create models that perform…