Related papers: BoxSnake: Polygonal Instance Segmentation with Box…

How to extract instance-level masks without instance-level supervision is the main challenge of weakly supervised instance segmentation (WSIS). Popular WSIS methods estimate a displacement field (DF) via learning inter-pixel relations and…

Image segmentation methods are usually trained with pixel-level annotations, which require significant human effort to collect. The most common solution to address this constraint is to implement weakly-supervised pipelines trained with…

We introduce the problem of weakly supervised Multi-Object Tracking and Segmentation, i.e. joint weakly supervised instance segmentation and multi-object tracking, in which we do not provide any kind of mask annotation. To address it, we…

Labeling pixel-wise object masks in videos is a resource-intensive and laborious process. Box-supervised Video Instance Segmentation (VIS) methods have emerged as a viable solution to mitigate the labor-intensive annotation process. . In…

We propose MonoBox, an innovative box-supervised segmentation method constrained by monotonicity to liberate its training from the user-unfriendly box-tightness assumption. In contrast to conventional box-supervised segmentation, where the…

Semantic segmentation is essential in computer vision for various applications, yet traditional approaches face significant challenges, including the high cost of annotation and extensive training for supervised learning. Additionally, due…

We introduce DiscoBox, a novel framework that jointly learns instance segmentation and semantic correspondence using bounding box supervision. Specifically, we propose a self-ensembling framework where instance segmentation and semantic…

Current instance segmentation methods rely heavily on pixel-level annotated images. The huge cost to obtain such fully-annotated images restricts the dataset scale and limits the performance. In this paper, we formally address…

In large-scale storehouses, precise instance masks are crucial for robotic bin picking but are challenging to obtain. Existing instance segmentation methods typically rely on a tedious process of scene collection, mask annotation, and…

Instance segmentation is the problem of detecting and delineating each distinct object of interest appearing in an image. Current instance segmentation approaches consist of ensembles of modules that are trained independently of each other,…

Training a computer vision system to segment a novel class typically requires collecting and painstakingly annotating lots of images with objects from that class. Few-shot segmentation techniques reduce the required number of images to…

Limited by the expensive labeling, polyp segmentation models are plagued by data shortages. To tackle this, we propose the mixed supervised polyp segmentation paradigm (MixPolyp). Unlike traditional models relying on a single type of…

In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled with bounding box annotations. It extends the approach of the well-known GrabCut method to include machine learning by…

Many two-stage instance segmentation heads predict a coarse 28x28 mask per instance, which is insufficient to capture the fine-grained details of many objects. To address this issue, PointRend and RefineMask predict a 112x112 segmentation…

We introduce a novel robotic system for improving unseen object instance segmentation in the real world by leveraging long-term robot interaction with objects. Previous approaches either grasp or push an object and then obtain the…

Limited by expensive pixel-level labels, polyp segmentation models are plagued by data shortage and suffer from impaired generalization. In contrast, polyp bounding box annotations are much cheaper and more accessible. Thus, to reduce…

We present an approach for road segmentation that only requires image-level annotations at training time. We leverage distant supervision, which allows us to train our model using images that are different from the target domain. Using…

Instance segmentation in remote sensing images is a long-standing challenge. Since horizontal bounding boxes introduce many interference objects, oriented bounding boxes (OBBs) are usually used for instance identification. However, based on…

Recently, progress in acquisition equipment such as LiDAR sensors has enabled sensing increasingly spacious outdoor 3D environments. Making sense of such 3D acquisitions requires fine-grained scene understanding, such as constructing…

To date, instance segmentation is dominated by twostage methods, as pioneered by Mask R-CNN. In contrast, one-stage alternatives cannot compete with Mask R-CNN in mask AP, mainly due to the difficulty of compactly representing masks, making…