Related papers: BoxSeg: Quality-Aware and Peer-Assisted Learning f…
Labeling objects with pixel-wise segmentation requires a huge amount of human labor compared to bounding boxes. Most existing methods for weakly supervised instance segmentation focus on designing heuristic losses with priors from bounding…
The realm of Weakly Supervised Instance Segmentation (WSIS) under box supervision has garnered substantial attention, showcasing remarkable advancements in recent years. However, the limitations of box supervision become apparent in its…
Weakly supervised instance segmentation using only bounding box annotations has recently attracted much research attention. Most of the current efforts leverage low-level image features as extra supervision without explicitly exploiting the…
Accurate defect segmentation is critical for industrial inspection, yet dense pixel-level annotations are rarely available. A common workaround is to convert inexpensive bounding boxes into pseudo-masks using foundation segmentation models…
Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks. Such pixel-accurate supervision demands expensive labeling effort and limits the…
Recently, several weakly supervised learning methods have been devoted to utilize bounding box supervision for training deep semantic segmentation models. Most existing methods usually leverage the generic proposal generators (e.g., dense…
We present Polite Teacher, a simple yet effective method for the task of semi-supervised instance segmentation. The proposed architecture relies on the Teacher-Student mutual learning framework. To filter out noisy pseudo-labels, we use…
Open-vocabulary instance segmentation aims at segmenting novel classes without mask annotations. It is an important step toward reducing laborious human supervision. Most existing works first pretrain a model on captioned images covering…
In this work, we present a novel and effective framework to facilitate object detection with the instance-level segmentation information that is only supervised by bounding box annotation. Starting from the joint object detection and…
How to estimate the quality of the network output is an important issue, and currently there is no effective solution in the field of human parsing. In order to solve this problem, this work proposes a statistical method based on the output…
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…
3D instance segmentation is crucial for understanding complex 3D environments, yet fully supervised methods require dense point-level annotations, resulting in substantial annotation costs and labor overhead. To mitigate this, box-level…
We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training. While this setting has been studied in the literature, here we show significantly stronger performance…
Semantic segmentation requires dense pixel-level annotations, which are costly and time-consuming to acquire. To address this, we present SeSAM, a framework that uses a foundational segmentation model, i.e. Segment Anything Model (SAM),…
Box-supervised instance segmentation has gained much attention as it requires only simple box annotations instead of costly mask or polygon annotations. However, existing box-supervised instance segmentation models mainly focus on…
Instance segmentation in videos, which aims to segment and track multiple objects in video frames, has garnered a flurry of research attention in recent years. In this paper, we present a novel weakly supervised framework with…
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…
Supervised deep learning performance is heavily tied to the availability of high-quality labels for training. Neural networks can gradually overfit corrupted labels if directly trained on noisy datasets, leading to severe performance…
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…
The Segment Anything Model (SAM) is a popular vision foundation model; however, its high computational and memory demands make deployment on resource-constrained devices challenging. While Post-Training Quantization (PTQ) is a practical…