Where are the Masks: Instance Segmentation with Image-level Supervision

Laradji, Issam H.; Vazquez, David; Schmidt, Mark

doi:10.48550/arxiv.1907.01430

Cited by 5 publications

(10 citation statements)

References 29 publications

(85 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike those method, we improve the naive PRM method [16] just relying on classification networks and still make significant improvements compared with other counterparts [18,27,28]. Furthermore, a series of experiments are performed as the WISE [40] to analyze M-PMF with respect to object size and object category, demonstrating the effectiveness of our approach. Some examples comparisons are shown in Figure 8.…”

Section: Statistical Analysis For M-pmfmentioning

confidence: 97%

Weakly supervised instance segmentation via peak mining and filtering

Huang,

Pan,

2024

IET Image Processing

View full text Add to dashboard Cite

Learning the full extent of pixel‐level instance response in a weakly supervised manner remains unsatisfactory. Peak response maps (PRMs) localizes the discriminative object regions but cannot provide complete instance information, suffering from incomplete segmentation and unreliable mask prediction by noisy proposal retrieval. This work tackles this challenging problem by mining diverse class peak responses that include more discriminative and complete object regions and retrieving more reliable proposals from noisy segment proposal galleries. First, the existing method is enhanced with two more classification branches, thus contributing to more diverse and abundant instance regions from peak response maps. The mined class peak responses from two of the branches are then merged to generate more complete peak response maps by a clustering approach in their deep feature space. Then, instance segmentation masks are retrieved from a noisy object segment proposal gallery with class confidence, which is calculated by a normal classifier to obtain cleaner mask prediction. Finally, the pseudo‐supervision can be used to train an instance segmentation network in a fully supervised manner. Experiments on the PASCAL VOC 2012 dataset and COCO dataset show that the approach works effectively and outperforms other counterparts by a margin of more than 6 %, 4%, and 3% with the mean average precision (mAP) at IoU threshold of 0.25, 0.5 and 0.75, respectively.

show abstract

Section: Statistical Analysis For M-pmfmentioning

confidence: 97%

Weakly supervised instance segmentation via peak mining and filtering

Huang,

Pan,

2024

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Tang et al [101] use a refinement learning strategy to select good quality proposals. C-MIL [108] introduces an optimization method to avoid selecting poor proposals, C-WSL [33] uses object count information to obtain the highest scoring proposals, WISE [63] that uses class activation maps to score proposals and LOOC [64] 16. Despite the valuable efforts of Detectron2 towards standardization and open-sourcing, we did find the framework overwhelming for some use-cases.…”

Section: Weakly-supervised Object Detectionmentioning

confidence: 99%

A Survey of Self-Supervised and Few-Shot Object Detection

Huang¹,

Laradji²,

Vázquez³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image. While few-shot object detection is about training a model on novel (unseen) object classes with little data, it still requires prior training on many labeled examples of base (seen) classes. On the other hand, self-supervised methods aim at learning representations from unlabeled data which transfer well to downstream tasks such as object detection. Combining the few-shot and self-supervised object detection is a promising research direction. In this survey, we review and characterize the most recent approaches on few-shot and self-supervised object detection. Then, we give our main takeaways and discuss future research directions.

show abstract

“…With them they generate a query to retrieve the best candidate among a set of pre-computed object proposals (MCG) [6]. Recently, [11] builds on PRMs by using the pseudo-masks to train Mask R-CNN [12] in a fully-supervised way, reaching better performance. Semi-Supervised Segmentation.…”

Section: Related Workmentioning

confidence: 99%

Mask-guided sample selection for semi-supervised instance segmentation

Bellver

Salvador

Torres

et al. 2020

Multimed Tools Appl

View full text Add to dashboard Cite

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 lower forms of supervision, such as bounding boxes or scribbles. Another option are semi-supervised methods, which leverage a large amount of unlabeled data and a limited number of strongly-labeled samples. In this second setup, samples to be strongly-annotated can be selected randomly or with an active learning mechanism that chooses the ones that will maximize the model performance. In this work, we propose a sample selection approach to decide which samples to annotate for semi-supervised instance segmentation. Our method consists in first predicting pseudo-masks for the unlabeled pool of samples, together with a score predicting the quality of the mask. This score is an estimate of the Intersection Over Union (IoU) of the segment with the ground truth mask. We study which samples are better to annotate given the quality score, and show how our approach outperforms a random selection, leading to improved performance for semi-supervised instance segmentation with low annotation budgets.

show abstract

Where are the Masks: Instance Segmentation with Image-level Supervision

Cited by 5 publications

References 29 publications

Weakly supervised instance segmentation via peak mining and filtering

Weakly supervised instance segmentation via peak mining and filtering

A Survey of Self-Supervised and Few-Shot Object Detection

Mask-guided sample selection for semi-supervised instance segmentation

Contact Info

Product

Resources

About