Related papers: Vision Transformers Are Good Mask Auto-Labelers

Weakly supervised instance labeling using only image-level labels, in lieu of expensive fine-grained pixel annotations, is crucial in several applications including medical image analysis. In contrast to conventional instance segmentation…

Large-scale annotation of image segmentation datasets is often prohibitively expensive, as it usually requires a huge number of worker hours to obtain high-quality results. Abundant and reliable data has been, however, crucial for the…

Most methods for object instance segmentation require all training examples to be labeled with segmentation masks. This requirement makes it expensive to annotate new categories and has restricted instance segmentation models to ~100…

This paper introduces a novel approach to learning instance segmentation using extreme points, i.e., the topmost, leftmost, bottommost, and rightmost points, of each object. These points are readily available in the modern bounding box…

Manually annotating object segmentation masks is very time consuming. Interactive object segmentation methods offer a more efficient alternative where a human annotator and a machine segmentation model collaborate. In this paper we make…

Pathological image analysis is an important process for detecting abnormalities such as cancer from cell images. However, since the image size is generally very large, the cost of providing detailed annotations is high, which makes it…

Weakly supervised segmentation methods using bounding box annotations focus on obtaining a pixel-level mask from each box containing an object. Existing methods typically depend on a class-agnostic mask generator, which operates on the…

3D instance segmentation is an important task for real-world applications. To avoid costly manual annotations, existing methods have explored generating pseudo labels by transferring 2D masks from foundation models to 3D. However, this…

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…

Vision Language Models (VLMs) have demonstrated remarkable performance in open-world zero-shot visual recognition. However, their potential in space-related applications remains largely unexplored. In the space domain, accurate manual…

Recognizing multiple objects in an image is challenging due to occlusions, and becomes even more so when the objects are small. While promising, existing multi-label image recognition models do not explicitly learn context-based…

As we all know, multi-view data is more expressive than single-view data and multi-label annotation enjoys richer supervision information than single-label, which makes multi-view multi-label learning widely applicable for various pattern…

Histopathology image analysis plays a critical role in cancer diagnosis and treatment. To automatically segment the cancerous regions, fully supervised segmentation algorithms require labor-intensive and time-consuming labeling at the pixel…

Multiple instance learning (MIL) can reduce the need for costly annotation in tasks such as semantic segmentation by weakening the required degree of supervision. We propose a novel MIL formulation of multi-class semantic segmentation…

We present a mask-piloted Transformer which improves masked-attention in Mask2Former for image segmentation. The improvement is based on our observation that Mask2Former suffers from inconsistent mask predictions between consecutive decoder…

Masked image modeling is a promising self-supervised learning method for visual data. It is typically built upon image patches with random masks, which largely ignores the variation of information density between them. The question is: Is…

Active learning (AL) is a label-efficient machine learning paradigm that focuses on selectively annotating high-value instances to maximize learning efficiency. Its effectiveness can be further enhanced by incorporating weak supervision,…

Segmenting unknown or anomalous object instances is a critical task in autonomous driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without…

Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual representation learning. It operates by randomly masking image patches and reconstructing these masked patches using the unmasked ones. A key limitation…

Manually annotating object segmentation masks is very time-consuming. While interactive segmentation methods offer a more efficient alternative, they become unaffordable at a large scale because the cost grows linearly with the number of…