Weakly supervised object detector learning with model drift detection

By Parthipan Siva, Tao A. Xiang. 2011

159 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Extreme Clicking for Efficient Object Annotation (2017, background): “Weakly-supervised object localization techniques (WSOL) can be used to train object detectors from image-level labels only (without bounding boxes) [5, 11, 14, 55, 59].”
Weakly Supervised Object Localization with Multi-Fold Multiple Instance Learning (2015, neutral): “Siva and Xiang [45] propose to initially select one of the candidate windows sampled using the objectness method at each image such that an objective function based on intra-class and inter-class pairwise similarities is maximized.”
Unsupervised object discovery and localization in the wild: Part-based matching with bottom-up region proposals (2015, methodology): “We first report separate-class results, and compare our results to those of the state of the arts in weakly-supervised localization [9, 36, 43, 47, 45, 46, 56] and colocalization [27] in Table 6.”
Weakly-supervised Discovery of Visual Pattern Configurations (2014, result): “Table 1 compares our detection results against two baseline methods [23, 27] which report the result on the full dataset.”
Large-Scale Weakly Supervised Object Localization via Latent Category Learning (2015, methodology): “Among these methods, the one popularly used in many weakly supervised localization methods [3], [7], [8] is the one proposed by Alexe et al. [37], who present a generic objectness measure by combining multiple image cues in a Bayesian framework.”
Multi-fold MIL Training for Weakly Supervised Object Localization (2014, unknown): “’12 [23] 30.8 25.0 — 3.6 — 26.0 — — — — — — 21.3 29.9 — — — — — — 15.0 Siva and Xiang’11 [29] 13.4 44.0 3.1 3.1 0.0 31.2 43.9 7.1 0.1 9.3 9.9 1.5 [22] are based on external video data for training.”
C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection (2019, background): “WSOD approaches only require image category annotations indicating the presence or absence of a category of objects in images, significantly reducing human involvement by omitting labor-intensive bounding-box annotations [6,12,27–29,40].”
From Discriminant to Complete: Reinforcement Searching-Agent Learning for Weakly Supervised Object Detection (2020, background): “For example, Siva and Xiang [25] introduce the objectness, intraimage similarity, and interimage variance to mine informative object regions for learning the object detector.”
ConceptLearner: Discovering visual concepts from weakly labeled image collections (2014, methodology): “Another two most relevant comparison methods are the webly supervised method [10] and video supervised method [30].”
Weakly Supervised Object Localization Using Things and Stuff Transfer (2017, unknown): “As in most previous WSOL methods [8, 9, 3, 4, 10, 11, 12, 13, 14, 28], our scheme returns exactly one bounding-box per class per training image.”
Weakly Supervised Object Localization and Detection: A Survey (2021, unknown): “In [136], Siva et al. propose an intra-class metric and an inter-class metric to initialize the potential object locations.”
Sampling Techniques for Large-Scale Object Detection From Sparsely Annotated Objects (2018, methodology): “Prediction results of a network are used to train an object detector with limited annotation in many previous works [20, 22, 2, 3, 23].”
Edge Boxes: Locating Object Proposals from Edges (2014, background): “Another popular use is for weakly supervised learning [20,21], where by limiting the number of candidate regions, learning with less supervision becomes feasible.”
On learning to localize objects with minimal supervision (2014, unknown): “More recent work, such as (Siva & Xiang, 2011; Siva et al., 2012), attempts to learn detectors, or simply automatically generate bounding box annotations from much more challenging datasets such as PASCAL VOC (Everingham et al., 2010).”
Revisiting Knowledge Transfer for Training Object Class Detectors (2017, methodology): “Our scheme improves over previous usage of manually engineered object proposals and their associated objectness score [1, 10] in WSOL in two ways: (1) by using trained proposals and objectness scoring function trained on source classes; (2) generalizing the common use of a single classagnostic objec”
Learning Everything about Anything: Webly-Supervised Visual Concept Learning (2014, methodology): “Weakly-supervised object localization: The idea of training detection models from images and videos without bounding boxes has received renewed attention [2, 36, 39, 45] due to the recent success of the DPM detector [18].”
Unconstrained Salient Object Detection via Proposal Subset Optimization (2016, background): “in applications like weakly supervised localization [15, 44]), how proposals are filtered can greatly affect the hit rate.”
Weakly Supervised Object Localization with Latent Category Learning (2014, methodology): “, exhaustive search [20, 21], multiple instance learning [13,28,34], inter-intra-class modeling [5,9,23,28,29] and topic model [25,30].”
Weakly Supervised Cascaded Convolutional Networks (2016, methodology): “Weakly supervised detection: In the last decade, several weakly supervised object detection methods have been studied using multiple instance learning algorithms [4, 5, 29, 30].”