We believe our dataset provides a rich testbed to study UDA for part segmentation and will help to significantly push forward research in this area.
Specifically, given a training image, we find a set of similar images that show instances of the same object category in the same pose, through an affine alignment of their corresponding feature maps.
For the Waymo Open Dataset, we achieve a bird-eyes-view (BEV) detection AP of 80. 73 and trajectory prediction average displacement error (ADE) of 33. 67cm for pedestrians, which establish the state-of-the-art for both tasks.
Our experimental results demonstrate that the proposed extensions increase the model's performance at localizing occluders as well as at classifying partially occluded objects.
Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers with an overall five-year survival rate of 8%.
Trauma is the worldwide leading cause of death and disability in those younger than 45 years, and pelvic fractures are a major source of morbidity and mortality.
In this work, we combine DCNNs and compositional object models to retain the best of both approaches: a discriminative model that is robust to partial occlusion and mask attacks.
The critical principle of ghost networks is to apply feature-level perturbations to an existing model to potentially create a huge set of diverse models.
In this paper, we propose that the robustness of a face detector against hard faces can be improved by learning small faces on hard images.
Ranked #2 on Face Detection on PASCAL Face
1 code implementation • 31 Mar 2018 • Alexey Kurakin, Ian Goodfellow, Samy Bengio, Yinpeng Dong, Fangzhou Liao, Ming Liang, Tianyu Pang, Jun Zhu, Xiaolin Hu, Cihang Xie, Jian-Yu Wang, Zhishuai Zhang, Zhou Ren, Alan Yuille, Sangxia Huang, Yao Zhao, Yuzhe Zhao, Zhonglin Han, Junjiajia Long, Yerkebulan Berdibekov, Takuya Akiba, Seiya Tokui, Motoki Abe
To accelerate research on adversarial examples and robustness of machine learning classifiers, Google Brain organized a NIPS 2017 competition that encouraged researchers to develop new methods to generate adversarial examples as well as to develop new ways to defend against them.
We hope that our proposed attack strategy can serve as a strong benchmark baseline for evaluating the robustness of networks to adversaries and the effectiveness of different defense methods in the future.
Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module.
Our method is by introducing computation orderings to the channels within convolutional layers or blocks, based on which we gradually compute the outputs in a channel-wise manner.
We use clustering algorithms to study the population activities of the features and extract a set of visual concepts which we show are visually tight and correspond to semantic parts of vehicles.
The first layer extracts the evidence of local visual cues, and the second layer performs a voting mechanism by utilizing the spatial relationship between visual cues and semantic parts.
Our observation is that both segmentation and detection are based on classifying multiple targets on an image (e. g., the basic target is a pixel or a receptive field in segmentation, and an object proposal in detection), which inspires us to optimize a loss function over a set of pixels/proposals for generating adversarial perturbations.
14 code implementations • 3 Oct 2016 • Nicolas Papernot, Fartash Faghri, Nicholas Carlini, Ian Goodfellow, Reuben Feinman, Alexey Kurakin, Cihang Xie, Yash Sharma, Tom Brown, Aurko Roy, Alexander Matyasko, Vahid Behzadan, Karen Hambardzumyan, Zhishuai Zhang, Yi-Lin Juang, Zhi Li, Ryan Sheatsley, Abhibhav Garg, Jonathan Uesato, Willi Gierke, Yinpeng Dong, David Berthelot, Paul Hendricks, Jonas Rauber, Rujun Long, Patrick McDaniel
An adversarial example library for constructing attacks, building defenses, and benchmarking both
We address the key question of how object part representations can be found from the internal states of CNNs that are trained for high-level tasks, such as object classification.