Evaluating Weakly Supervised Object Localization Methods Right

Choe, Jong‐In; Oh, Seong Joon; Lee, Seungho; Chun, Sanghyuk; Akata, Zeynep; Shim, Hyunjung

doi:10.1109/cvpr42600.2020.00320

Cited by 161 publications

(254 citation statements)

References 35 publications

Supporting

Mentioning

232

Contrasting

Order By: Relevance

“…Setting the bounding box The output of g is map M in range 0 to 1, obtained by the sigmoid activation function. In order to derive a bounding box from this map, we follow the method of [6,7,29]. First, a threshold τ is calculated as…”

Section: Methods II (Siamese Network)mentioning

confidence: 99%

“…Previous WSOL works have been criticized by [7] for selecting the best checkpoint and the hyperparameters by considering the test data. It also offers an evaluation metric for weakly supervised segmentation where instead of bounding-box annotation, a foreground-background mask is given.…”

Section: Related Workmentioning

confidence: 99%

“…Very recently, [6] presented a new method for weighting the feature maps. Evaluation is done following the stringent settings presented by [7], and weakly-supervised segmentation results are presented on Oxford-flower102 [26].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Learning a Weight Map for Weakly-Supervised Localization

Shaharabany¹,

Wolf²

2021

Preprint

View full text Add to dashboard Cite

In the weakly supervised localization setting, supervision is given as an image-level label. We propose to employ an image classifier f and to train a generative network g that outputs, given the input image, a per-pixel weight map that indicates the location of the object within the image. Network g is trained by minimizing the discrepancy between the output of the classifier f on the original image and its output given the same image weighted by the output of g. The scheme requires a regularization term that ensures that g does not provide a uniform weight, and an early stopping criterion in order to prevent g from over-segmenting the image. Our results indicate that the method outperforms existing localization methods by a sizable margin on the challenging fine-grained classification datasets, as well as a generic image recognition dataset. Additionally, the obtained weight map is also state-of-the-art in weakly supervised segmentation in fine-grained categorization datasets.

show abstract

Section: Methods II (Siamese Network)mentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning a Weight Map for Weakly-Supervised Localization

Shaharabany¹,

Wolf²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Then the evaluation results of precision and recall can be calculated. In addition, several evaluation metrics are adopted to indicate if the number of location points is incorrect, such as Mean Absolute Error (MAE), Root Mean Squared Error(RMSE), and Mean Absolute Percent Error (MAPE) [34].…”

Section: B Object As Pointmentioning

confidence: 99%

P2P-Loc: Point to Point Tiny Person Localization

Yu¹,

Wu²,

Ye³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Our weak supervision is image-level multi-labels without pixel-level annotations, that is, the exact position of each component is unknown. A similar scenario is widely adopted in many weakly supervised vision recognition tasks; such as weakly supervised object localization [41], [42], weakly supervised object detection [43], or weakly supervised semantic segmentation [44], [45]. These weakly supervised vision recognition techniques have shown that with only image-level weak supervision, they can achieve a reasonable localization ability, for example, locating the target objects in the image.…”

Section: Related Workmentioning

confidence: 99%

Few-shot Font Generation with Weakly Supervised Localized Representations

Park¹,

Chun²,

Cha³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Automatic few-shot font generation aims to solve a well-defined, real-world problem because manual font designs are expensive and sensitive to the expertise of designers. Existing methods learn to disentangle style and content elements by developing a universal style representation for each font style. However, this approach limits the model in representing diverse local styles, because it is unsuitable for complicated letter systems, for example, Chinese, whose characters consist of a varying number of components (often called "radical") -with a highly complex structure. In this paper, we propose a novel font generation method that learns localized styles, namely component-wise style representations, instead of universal styles. The proposed style representations enable the synthesis of complex local details in text designs. However, learning component-wise styles solely from a few reference glyphs is infeasible when a target script has a large number of components, for example, over 200 for Chinese. To reduce the number of required reference glyphs, we represent component-wise styles by a product of component and style factors, inspired by low-rank matrix factorization. Owing to the combination of strong representation and a compact factorization strategy, our method shows remarkably better few-shot font generation results (with only eight reference glyphs) than other state-of-the-art methods. Moreover, strong locality supervision, for example, location of each component, skeleton, or strokes, was not utilized. The source code is available at https://github.com/clovaai/lffont and https://github.com/clovaai/fewshot-font-generation.

show abstract

Evaluating Weakly Supervised Object Localization Methods Right

Cited by 161 publications

References 35 publications

Learning a Weight Map for Weakly-Supervised Localization

Learning a Weight Map for Weakly-Supervised Localization

P2P-Loc: Point to Point Tiny Person Localization

Few-shot Font Generation with Weakly Supervised Localized Representations

Contact Info

Product

Resources

About