Semi-Supervised Self-Training of Object Detection Models

Rosenberg, C.; Hebert, Martial; Schneiderman, Henry

doi:10.1109/acvmot.2005.107

Cited by 700 publications

(468 citation statements)

References 8 publications

Supporting

Mentioning

442

Contrasting

Unclassified

Order By: Relevance

“…They controls how aggressive the automatic training process is. Similar parameters also exist in other approaches of automatically training scene specific detectors [10,11,12,13,14,15,16]. Our approach has robustness to these parameters within certain range.…”

Section: Conclusion and Discussionmentioning

confidence: 78%

“…By calculating the frame difference as 0.5(|I t − I t−50 | + I t − I t+50 |), moving pixels inside a detection window are thresholded and counted. Similar to other self-training [15,13] or co-training [11,10,16,21] frameworks, the confident positive examples are found by thresholding L p (z) > L 0 . The larger the threshold is, the more conservative the strategy of selecting examples is.…”

Section: Confident Positive Examples Of Pedestriansmentioning

confidence: 99%

“…In order to effectively improve the performance, the training examples selected by the automatic labeler must be reliable and informative to the detector. Semi-supervised selftraining was used in [15]. Examples confidently classified by the detector were used to re-train the detector.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Automatic adaptation of a generic pedestrian detector to a specific traffic scene

2011

View full text Add to dashboard Cite

In recent years significant progress has been made learning generic pedestrian detectors from manually labeled large scale training sets. However, when a generic pedestrian detector is applied to a specific scene where the testing data does not match with the training data because of variations of viewpoints, resolutions, illuminations and backgrounds, its accuracy may decrease greatly. In this paper, we propose a new framework of adapting a pre-trained generic pedestrian detector to a specific traffic scene by automatically selecting both confident positive and negative examples from the target scene to re-train the detector iteratively. An important feature of the proposed framework is to utilize unsupervisedly learned models of vehicle and pedestrian paths, together with multiple other cues such as locations, sizes, appearance and motions to select new training samples. The information of scene structures increases the reliability of selected samples and is complementary to the appearance-based detector. However, it was not well explored in previous studies. In order to further improve the reliability of selected samples, outliers are removed through multiple hierarchical clustering steps. The effectiveness of different cues and clustering steps is evaluated through experiments. The proposed approach significantly improves the accuracy of the generic pedestrian detector and also outperforms the scene specific detector retrained using background subtraction. Its results are comparable with the detector trained using a large number of manually labeled frames from the target scene.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 78%

Section: Confident Positive Examples Of Pedestriansmentioning

confidence: 99%

See 1 more Smart Citation

Automatic adaptation of a generic pedestrian detector to a specific traffic scene

2011

View full text Add to dashboard Cite

show abstract

“…In the self-training approach, a classifier is trained on the labeled data and then used to classify the unlabeled ones. The most confident (now labeled) unlabeled points are added to the training set, together with their predictive labels, and the process is repeated until convergence [5]. Approaches based on co-training [2] assume that the features describing the objects can be divided in two subsets such that each of them is sufficient to train a good classifier, and that the two sets are conditionally independent given the class attribute.…”

Section: Learning From Labeled and Unlabeled Datamentioning

confidence: 99%

Using Weighted Nearest Neighbor to Benefit from Unlabeled Data

Driessens

Reutemann

Pfahringer

et al. 2006

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. The development of data-mining applications such as textclassification and molecular profiling has shown the need for machine learning algorithms that can benefit from both labeled and unlabeled data, where often the unlabeled examples greatly outnumber the labeled examples. In this paper we present a two-stage classifier that improves its predictive accuracy by making use of the available unlabeled data. It uses a weighted nearest neighbor classification algorithm using the combined example-sets as a knowledge base. The examples from the unlabeled set are "pre-labeled" by an initial classifier that is build using the limited available training data. By choosing appropriate weights for this prelabeled data, the nearest neighbor classifier consistently improves on the original classifier.

show abstract

“…Our work does not require pixel-level labeled data. In [17], learning requires both pixel-level labeled data and frame-level labeled data. An object detector is initially trained on the pixel-level labeled data, and the learned model is used to estimate labels for the frame-level labeled data.…”

Section: Introductionmentioning

confidence: 99%

VideoCut: Removing Irrelevant Frames by Discovering the Object of Interest

Liu

Hua

Chen

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We propose a novel method for removing irrelevant frames from a video given user-provided frame-level labeling for a very small number of frames. We first hypothesize a number of candidate areas which possibly contain the object of interest, and then figure out which area(s) truly contain the object of interest. Our method enjoys several favorable properties. First, compared to approaches where a single descriptor is used to describe a whole frame, each area's feature descriptor has the chance of genuinely describing the object of interest, hence it is less affected by background clutter. Second, by considering the temporal continuity of a video instead of treating the frames as independent, we can hypothesize the location of the candidate areas more accurately. Third, by infusing prior knowledge into the topic-motion model, we can precisely follow the trajectory of the object of interest. This allows us to largely reduce the number of candidate areas and hence reduce the chance of overfitting the data during learning. We demonstrate the effectiveness of the method by comparing it to several other semi-supervised learning approaches on challenging video clips.

show abstract

Semi-Supervised Self-Training of Object Detection Models

Cited by 700 publications

References 8 publications

Automatic adaptation of a generic pedestrian detector to a specific traffic scene

Automatic adaptation of a generic pedestrian detector to a specific traffic scene

Using Weighted Nearest Neighbor to Benefit from Unlabeled Data

VideoCut: Removing Irrelevant Frames by Discovering the Object of Interest

Contact Info

Product

Resources

About