Forget and Diversify: Regularized Refinement for Weakly Supervised Object Detection

Son, Jae Sung; Kim, Daniel; Lee, Solae; Kwak, Suha; Cho, Minsu; Han, Bohyung

doi:10.1007/978-3-030-20870-7_39

Cited by 2 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, this technique is designed to find only a single object class and instance conceptually and often fails to solve the problems involving multiple labels and objects. Various ap-proaches [23,34,35,36,38] tackle this issue by incorporating additional components, but they are still prone to focus on the discriminative parts of objects instead of whole object regions. Recently, There are several research integrating semantic segmentation to improve detection performance [10,29,33,40].…”

Section: Weakly Supervised Object Detectionmentioning

confidence: 99%

Weakly Supervised Instance Segmentation by Deep Community Learning

Hwang

Kim

Son

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

We present a weakly supervised instance segmentation algorithm based on deep community learning with multiple tasks. This task is formulated as a combination of weakly supervised object detection and semantic segmentation, where individual objects of the same class are identified and segmented separately. We address this problem by designing a unified deep neural network architecture, which has a positive feedback loop of object detection with bounding box regression, instance mask generation, instance segmentation, and feature extraction. Each component of the network makes active interactions with others to improve accuracy, and the end-to-end trainability of our model makes our results more robust and reproducible. The proposed algorithm achieves state-of-the-art performance in the weakly supervised setting without any additional training such as Fast R-CNN and Mask R-CNN on the standard benchmark dataset.

show abstract

Section: Weakly Supervised Object Detectionmentioning

confidence: 99%

Weakly Supervised Instance Segmentation by Deep Community Learning

Hwang

Kim

Son

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast, our method covers the whole object delicately without extending to background. [6,7,8,9,10,11,12]. Especially, weakly supervised object localization (WSOL) is a challenging task that pursues both classification and the localization of the target object where the training datasets provide only the class labels.…”

Section: Introductionmentioning

confidence: 99%

In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object Localization

Lee

et al. 2021

Computer Vision – ACCV 2020

View full text Add to dashboard Cite

Weakly supervised object localization (WSOL) aims to localize the target object using only the image-level supervision. Recent methods encourage the model to activate feature maps over the entire object by dropping the most discriminative parts. However, they are likely to induce excessive extension to the backgrounds which leads to over-estimated localization. In this paper, we consider the background as an important cue that guides the feature activation to cover the sophisticated object region and propose contrastive attention loss. The loss promotes similarity between foreground and its dropped version, and, dissimilarity between the dropped version and background. Furthermore, we propose foreground consistency loss that penalizes earlier layers producing noisy attention regarding the later layer as a reference to provide them with a sense of backgroundness. It guides the early layers to activate on objects rather than locally distinctive backgrounds so that their attentions to be similar to the later layer. For better optimizing the above losses, we use the non-local attention blocks to replace channel-pooled attention leading to enhanced attention maps considering the spatial similarity. Last but not least, we propose to drop background regions in addition to the most discriminative region. Our method achieves state-of-theart performance on CUB-200-2011 and ImageNet benchmark datasets regarding top-1 localization accuracy and MaxBoxAccV2, and we provide detailed analysis on our individual components. The code will be publicly available online for reproducibility.

show abstract

Forget and Diversify: Regularized Refinement for Weakly Supervised Object Detection

Cited by 2 publications

References 35 publications

Weakly Supervised Instance Segmentation by Deep Community Learning

Weakly Supervised Instance Segmentation by Deep Community Learning

In-sample Contrastive Learning and Consistent Attention for Weakly Supervised Object Localization

Contact Info

Product

Resources

About