Weakly Supervised Object Detection with Posterior Regularization

By Hakan Bilen, Marco Pedersoli, Tinne Tuytelaars. 2014

133 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning (2015, neutral): “, [4], [8], [12], [15], [17], [35], [37], [38], [40], [43], [45], [46], [47], [53].”
Weakly Supervised Cascaded Convolutional Networks (2016, methodology): “[4] proposed a CNN-based convex optimization method to solve the problem to escape from getting stuck in local minima.”
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].”
Visual and Semantic Knowledge Transfer for Large Scale Semi-Supervised Object Detection (2016, background): “Recently, there have been several studies in CNN-based object detection in a weakly-supervised setting [27], [28], [29], [30], [31], i.”
We Don’t Need No Bounding-Boxes: Training Object Class Detectors Using Only Human Verification (2016, methodology): “Recent work on WSOL [4, 5, 8, 48, 49, 60] has shown remarkable progress, mainly because of the use of Convolutional Neural Nets (CNN [20, 28]), which greatly improve visual recognition tasks.”
Weakly Supervised Deep Detection Networks (2015, methodology): “The majority of previous work [31, 32, 1, 36, 2] use the Caffe reference CNN model [17], which is comparable to model S in this paper, as a black box to extract features over SSW proposals.”
C-MIDN: Coupled Multiple Instance Detection Network With Segmentation Guidance for Weakly Supervised Object Detection (2019, methodology): “Traditional Multiple Instance Learning To achieve localization with only image-level annotations provided, most of previous works [17, 7, 28, 5, 14, 3, 2, 24, 27] formulate WSOD as an MIL problem [10].”
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].”
Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes (2017, background): “Some applications include weakly supervised segmentation [44, 49] and detection [5], and rule-regularized training of neural networks [29].”
Domain Adaptation for Semantic Segmentation of Urban Scenes (2017, background): “Some applications include weakly supervised segmentation [44, 49] and detection [5], and rule-regularized training of neural networks [29].”
Weakly Supervised Object Localization and Detection: A Survey (2021, unknown): “Early methods in this ﬁled usually add prior knowledge [137] or post regularization [6] on the classic MIL models, such as LSVM [185], while the current research obtains the break-through by building deep MIL models [168], [175], [216].”
Y Qualification Main task Y Return N N Y User qualified ? N Feedback Pass ? Pass ? Annotator training Annotating images (2017, methodology): “State-of-the-art WSOL approaches based on AlexNet architecture [34] perform as follows.”
Cross-Modal Supervision for Learning Active Speaker Detection in Video (2016, methodology): “In the absence of information about which upper body bounding box is associated with the active speaker in each frame, the problem can be posed as a structured training problem [7,8,9,12], in the presence of partially observed training data.”
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-Supervised Object and Action Localization (2017, methodology): “Weakly-supervised approaches have been proposed for various visual classification and localization tasks including object detection [55, 13, 9, 41, 3, 50, 43, 8, 32, 61, 40], semantic segmentation [33, 26] and visual attribute localization [2, 53, 57, 52, 39].”
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection (2019, background): “…the presence or absence of a category of objects in images, signiﬁcantly reducing human involvement by omitting labor-intensive bounding-box annotations [6,12,27–29 Despite extensive research over the past ﬁve years, WSOD remains an open problem, as indicated by the large performance gap ( ∼ 20”
Track and Transfer: Watching Videos to Simulate Strong Human Supervision for Weakly-Supervised Object Detection (2016, methodology): “We compare with state-of-the-art weakly-supervised detection methods [33, 34, 1, 37, 4] that use the same AlexNet CNN features pre-trained on ILSVRC 2012.”
ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization (2016, background): “[21] propose a relaxed version of MIL that softly labels object instances instead of choosing the highest scoring ones.”