Saliency Guided End-to-End Learning for Weakly Supervised Object Detection

Lai, Baisheng; Gong, Xiaojin

doi:10.24963/ijcai.2017/285

Cited by 26 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our approach with both two-step [1][2][3][4] and end-to-end [5][6][7][8][9][10] approaches. Top-3 results are indicated by green, red and blue colors.…”

Section: Comparison With Other State-of-the-artsmentioning

confidence: 99%

TS$$^{2}$$C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection

Wei

Shen

Cheng

et al. 2018

Lecture Notes in Computer Science

113

131

View full text Add to dashboard Cite

This work provides a simple approach to discover tight object bounding boxes with only image-level supervision, called Tight box mining with Surrounding Segmentation Context (TS 2 C). We observe that object candidates mined through current multiple instance learning methods are usually trapped to discriminative object parts, rather than the entire object. TS 2 C leverages surrounding segmentation context derived from weakly-supervised segmentation to suppress such lowquality distracting candidates and boost the high-quality ones. Specifically, TS 2 C is developed based on two key properties of desirable bounding boxes: 1) high purity, meaning most pixels in the box are with high object response, and 2) high completeness, meaning the box covers high object response pixels comprehensively. With such novel and computable criteria, more tight candidates can be discovered for learning a better object detector. With TS 2 C, we obtain 48.0% and 44.4% mAP scores on VOC 2007 and 2012 benchmarks, which are the new state-of-the-arts.

show abstract

“…We compare our approach with both two-step [1][2][3][4] and end-to-end [5][6][7][8][9][10] approaches. Top-3 results are indicated by green, red and blue colors.…”

Section: Comparison With Other State-of-the-artsmentioning

confidence: 99%

TS$$^{2}$$C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection

Wei

Shen

Cheng

et al. 2018

Lecture Notes in Computer Science

113

131

View full text Add to dashboard Cite

show abstract

“…However, WSDDN only uses an image-level classification loss which makes it tend to recognize the most discriminative parts. To address the problem, [Diba et al, 2017] and [Lai and Gong, 2017] introduce salient segmentation attention maps to regularize the training. The introduced segmentation regularization is helpful but not enough to address the huge gap between those discriminative parts and the complete bounding boxes.…”

Section: Weakly Supervised Object Detectionmentioning

confidence: 99%

Low Shot Box Correction for Weakly Supervised Object Detection

Pan

Wang

Ding

et al. 2019

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Weakly supervised object detection (WSOD) has been widely studied but the accuracy of state-of-art methods remains far lower than strongly supervised methods. One major reason for this huge gap is the incomplete box detection problem which arises because most previous WSOD models are structured on classification networks and therefore tend to recognize the most discriminative parts instead of complete bounding boxes. To solve this problem, we define a low-shot weakly supervised object detection task and propose a novel low-shot box correction network to address it. The proposed task enables to train object detectors on a large data set all of which have image-level annotations, but only a small portion or few shots have box annotations. Given the low-shot box annotations, we use a novel box correction network to transfer the incomplete boxes into complete ones. Extensive empirical evidence shows that our proposed method yields state-of-art detection accuracy under various settings on the PASCAL VOC benchmark.

show abstract

“…The task specific loss function is decomposed over the bounding box as shown in equation (5) of the main paper. Therefore, we re-write the above equation as (20) DIV ∆ (Pr c , Pr c )…”

Section: Diversity Between Prediction Net and Conditional Netmentioning

confidence: 99%

Dissimilarity Coefficient Based Weakly Supervised Object Detection

Arun

Jawahar

Kumar

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

We consider the problem of weakly supervised object detection, where the training samples are annotated using only image-level labels that indicate the presence or absence of an object category. In order to model the uncertainty in the location of the objects, we employ a dissimilarity coefficient based probabilistic learning objective. The learning objective minimizes the difference between an annotation agnostic prediction distribution and an annotation aware conditional distribution. The main computational challenge is the complex nature of the conditional distribution, which consists of terms over hundreds or thousands of variables. The complexity of the conditional distribution rules out the possibility of explicitly modeling it. Instead, we exploit the fact that deep learning frameworks rely on stochastic optimization. This allows us to use a state of the art discrete generative model that can provide annotation consistent samples from the conditional distribution. Extensive experiments on PASCAL VOC 2007 and 2012 data sets demonstrate the efficacy of our proposed approach.

show abstract

Saliency Guided End-to-End Learning for Weakly Supervised Object Detection

Cited by 26 publications

References 0 publications

TS$$^{2}$$C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection

TS$$^{2}$$C: Tight Box Mining with Surrounding Segmentation Context for Weakly Supervised Object Detection

Low Shot Box Correction for Weakly Supervised Object Detection

Dissimilarity Coefficient Based Weakly Supervised Object Detection

Contact Info

Product

Resources

About