Towards Open World Object Detection

Joseph, K J; Khan, Salman; Khan, Fahad Shahbaz; Balasubramanian, Vineeth N

doi:10.1109/cvpr46437.2021.00577

Cited by 350 publications

(223 citation statements)

References 44 publications

Supporting

Mentioning

222

Contrasting

Order By: Relevance

“…We consider adding fixed Gaussian noise to the ID features, adding trainable noise to the ID features where the noise is trained to push the outliers away from ID features, and using fixed Gaussian noise as outliers. Lastly, for type III, we directly use the negative proposals in the ROI head as the outliers for Equation 5, similar to Joseph et al (2021). We consider three variants: randomly sampling n negative proposals (n is the number of positive proposals), sampling n negative proposals with a larger probability, and using all the negative proposals.…”

Section: Evaluation On Object Detectionmentioning

confidence: 99%

“…OOD detection for object detection is currently underexplored. Joseph et al (2021) used energy score (Liu et al, 2020a) to identify the OOD data and then labeled them for incremental object detection. In contrast, VOS focuses on OOD detection and adopts a new unknown-aware training objective with a new test-time detection score.…”

Section: Related Workmentioning

confidence: 99%

“…Our learning framework is generally applicable to both object detectors and classification models. Moreover, Joseph et al (2021) used the negative proposals as unknown samples for model regularization, which is suboptimal as we show in Table 2. Harakeh & Waslander (2021); Riedlinger et al (2021) focused on uncertainty estimation for the localization regression, rather than OOD detection for classification problems.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

VOS: Learning What You Don't Know by Virtual Outlier Synthesis

Du¹,

Wang²,

Cai³

et al. 2022

Preprint

View full text Add to dashboard Cite

Out-of-distribution (OOD) detection has received much attention lately due to its importance in the safe deployment of neural networks. One of the key challenges is that models lack supervision signals from unknown data, and as a result, can produce overconfident predictions on OOD data. Previous approaches rely on real outlier datasets for model regularization, which can be costly and sometimes infeasible to obtain in practice. In this paper, we present VOS, a novel framework for OOD detection by adaptively synthesizing virtual outliers that can meaningfully regularize the model's decision boundary during training. Specifically, VOS samples virtual outliers from the low-likelihood region of the classconditional distribution estimated in the feature space. Alongside, we introduce a novel unknown-aware training objective, which contrastively shapes the uncertainty space between the ID data and synthesized outlier data. VOS achieves stateof-the-art performance on both object detection and image classification models, reducing the FPR95 by up to 7.87% compared to the previous best method. Code is available at https://github.com/deeplearning-wisc/vos.

show abstract

Section: Evaluation On Object Detectionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

VOS: Learning What You Don't Know by Virtual Outlier Synthesis

Du¹,

Wang²,

Cai³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Based on the Faster R-CNN, Joseph et al used an energy-based classification head and unknown-aware RPN to identify unknown objects. Furthermore, contrastive learning was performed in the feature space to learn discriminative clusters and add new classes in a continual [34].…”

Section: Related Workmentioning

confidence: 99%

A Novel Object Detection Method in City Aerial Image Based on Deformable Convolutional Networks

Zhou

Sun

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Unmanned Aerial Vehicle (UAV) has been widely applied for aerial object detection. Recently, this issue has become a research hot spot in the field of computer vision. Currently, the performance of conventional methods to detect small objects has reached a breakthrough point. Moreover, the dense distribution and large-scale variation of objects in aerial images significantly affect the detection accuracy. In order to resolve this problem, a novel structure based on the YOLOv3 is proposed in the present study. To this end, the backbone network is replaced by ResNet_vd50 to prevent information loss in the downsampling process. Then the backbone network is modified by deformable convolution to improve the detection ability of deformed objects. In this regard, SE attention is embedded in the ResNet_vd block to improve the expression ability of features. Furthermore, the Soft-NMS algorithm is introduced for bounding box fusion to resolve the occlusion problem. Finally, the MixUp method is used in the data augmentation stage to enrich the background information by fusing different images. Based on the obtained results, it is concluded that the proposed method has higher accuracy in aerial images than state of art object detection methods.

show abstract

“…Different from the open world setting in [23,24] which entirely concentrates on unknown classes, our proposed setting further considers a common phenomenon in known classes that a distributional discrepancy exists, apart from detecting unknown classes. Moreover, some existing studies about open set segmentation [25,26] also do not consider the distribution shift problem.…”

Section: The Property Of Unknown Pixelsmentioning

confidence: 99%

KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation

Chen¹,

Liu²,

Chen³

et al. 2021

Preprint

View full text Add to dashboard Cite

In semantic segmentation, we aim to train a pixel-level classifier to assign category labels to all pixels in an image, where labeled training images and unlabeled test images are from the same distribution and share the same label set. However, in an open world, the unlabeled test images probably contain unknown categories and have different distributions from the labeled images. Hence, in this paper, we consider a new, more realistic, and more challenging problem setting where the pixel-level classifier has to be trained with labeled images and unlabeled open-world images-we name it open world semantic segmentation (OSS). In OSS, the trained classifier is expected to identify unknown-class pixels and classify known-class pixels well. To solve OSS, we first investigate which distribution that unknown-class pixels obey. Then, motivated by the goodness-of-fit test, we use statistical measurements to show how a pixel fits the distribution of an unknown class and select highly-fitted pixels to form the unknown region in each image. Eventually, we propose an end-to-end learning framework, known-region-aware domain alignment (KRADA), to distinguish unknown classes while aligning distributions of known classes in labeled and unlabeled open-world images. The effectiveness of KRADA has been verified on two synthetic tasks and one COVID-19 segmentation task.

show abstract

Towards Open World Object Detection

Cited by 350 publications

References 44 publications

VOS: Learning What You Don't Know by Virtual Outlier Synthesis

VOS: Learning What You Don't Know by Virtual Outlier Synthesis

A Novel Object Detection Method in City Aerial Image Based on Deformable Convolutional Networks

KRADA: Known-region-aware Domain Alignment for Open-set Domain Adaptation in Semantic Segmentation

Contact Info

Product

Resources

About