Large-Scale Weakly Supervised Object Localization via Latent Category Learning

By Kaiqi Huang, Weiqiang Ren, Junge Zhang, S. Maybank. 2015

64 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

Extreme Clicking for Efficient Object Annotation (2017, background): “This setting is very cheap in terms of annotation time, but it produces lower quality object detectors, typically performing at only about half the level of accuracy achieved by training from bounding boxes [5, 11, 14, 55, 67].”
Global Weighted Average Pooling Bridges Pixel-level Localization and Image-level Classification (2018, methodology): “Weakly supervised object detection methods [15], [16], [17], [7], [8], [9], [10] are evolved from the region-based object detection frameworks [18], [19], [20], [21].”
Y Qualification Main task Y Return N N Y User qualified ? N Feedback Pass ? Pass ? Annotator training Annotating images (2017, background): “This setting is very cheap in terms of annotation time, but it produces lower quality object detectors, typically performing at only about half the level of accuracy achieved by training from bounding boxes [5, 11, 14, 55, 67].”
Weakly Supervised Object Localization Using Things and Stuff Transfer (2017, unknown): “Following [29, 8, 13, 14, 28], we describe the proposals by the output of the fc7 layer of the AlexNet CNN architecture [30].”
Weakly Supervised Object Localization and Detection: A Survey (2021, unknown): “While other approaches, e.g., [8], [110], [157], focus on developing weakly supervised learning frameworks for unconstrained object categories, i.e., learning frameworks can be extended to learn object detector for the given category-speciﬁc weakly-labelled training images.”
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection (2019, methodology): “LCL+Context [11] 48.”
We Don’t Need No Bounding-Boxes: Training Object Class Detectors Using Only Human Verification (2016, methodology): “Following the common protocol for WSOL experiments [8, 9, 12, 42, 60], we exclude trainval images that contain only difficult and truncated instances, ending up with 3550 images.”
Min-Entropy Latent Model for Weakly Supervised Object Detection (2018, methodology): “MILinear [25] 43.9 LCL+Context [16] 48.5 PDA [23] 49.8 WCCN [28] 52.6 Multi-fold MIL [11] 54.2 WSDDN [22] 54.2 ContextNet [24] 55.1 MELM 58.4 VGG16 PDA [23] 52.4 WSDDN [22] 53.5 WCCN [28] 56.7 MELM 61.4 improved the mAP of “MELM-L-RL” from 42.6% to 46.4% (+3.8%).”
Revisiting Knowledge Transfer for Training Object Class Detectors (2017, methodology): “Typical MIL implementations use as appearance model a linear SVM trained on CNN-features extracted from the object proposals [13, 6, 2, 3, 37, 44].”
LayerCAM: Exploring Hierarchical Class Activation Maps for Localization (2021, methodology): “Recently, a lot of WSOL methods [59], [60], [1], [8], [60], [61], [62], [63] utilizing attention methods have been proposed, such as CAM [1], Grad-CAM [2], and ACoL [8].”