Object Counting and Instance Segmentation With Image-Level Supervision

By Hisham Cholakkal, Guolei Sun, Fahad Shahbaz Khan, Ling Shao. 2019

133 citations recorded by the source corpus.

Common object counting in a natural scene is a challenging problem in computer vision with numerous real-world applications. Existing image-level supervised common object counting approaches only predict the global object count and rely on additional instance-level supervision to also determine object locations. We propose an image-level supervised approach that provides both the global object count and the spatial distribution of object instances by constructing an object category density map. Motivated by psychological studies, we further reduce image-level supervision using a limited object count information (up to four). To the best of our knowledge, we are the first to propose image-level supervised density map estimation for common object counting and demonstrate its effectiveness in image-level supervised instance segmentation. Comprehensive experiments are performed on the PASCAL VOC and COCO datasets. Our approach outperforms existing methods, including those using instance-level supervision, on both datasets for common object counting. Moreover, our approach improves state-of-the-art image-level supervised instance segmentation with a relative gain of 17.8% in terms of average best overlap, on the PASCAL VOC 2012 dataset.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Incremental Object Detection via Meta-Learning (2020, neutral): “Extending our methodology to single stage detectors [57], [58], [59] and incremental versions of related problem settings such as action recognition [60], object counting [61] and instance segmentation [62] are interesting and important research directions.”
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (2020, background): “Deep learning has achieved great success in a variety of computer vision tasks [20,12,43,35,45,44,25,24,53,52].”
MoVie: Revisiting Modulated Convolutions for Visual Counting and Beyond (2021, background): “3, MoVie outperforms CountSeg on COCO with a signiﬁcant margin on three RMSE metrics.”
Pointly-Supervised Instance Segmentation (2021, background): “Manual annotation of object masks for training is signiﬁcantly more complex and time-consuming than other forms of image annotation like image-level categories [1, 9, 13, 15, 34, 61, 62] or per-object bounding boxes [2,21,23,53].”
Guided Attention Network for Object Detection and Counting on Drones (2019, unknown): “Object counting methods aim to predict the total number of objects in different categories existing in images, such as pedestrian counting [20, 26, 46, 50], vehicle counting [12, 49], goods counting [11, 21] and general object counting [2, 3, 18].”
Enriched Feature Guided Refinement Network for Object Detection (2019, background): “Convolutional neural networks (CNNs) [36, 18, 9, 38, 29, 37] based object detectors [14, 15, 32, 17, 33, 8, 27, 2] have shown outstanding re-sults in recent years.”
LayerCAM: Exploring Hierarchical Class Activation Maps for Localization (2021, background): “The effectiveness of the attention methods [1], [2] or attention modules [23], [24], [25] beneﬁt a lot of vision tasks [26], [27], [28], [29], [30], [31], [32].”