17 citations · 133 across the 50 of their papers we have counts for
9 papers · 1 filter
Robust Instance Segmentation through Reasoning about Multi-Object Occlusion
Xiaoding Yuan, Adam Kortylewski, Yihong Sun +1
Analyzing complex scenes with Deep Neural Networks is a challenging task, particularly when images contain multiple objects that partially occlude each other. Existing approaches t…
Robustness Out of the Box: Compositional Representations Naturally Defend Against Black-Box Patch Attacks
Christian Cosgrove, Adam Kortylewski, Chenglin Yang +1
Patch-based adversarial attacks introduce a perceptible but localized change to the input that induces misclassification. While progress has been made in defending against impercep…
Unsupervised Part Discovery via Feature Alignment
Mengqi Guo, Yutong Bai, Zhishuai Zhang +2
Understanding objects in terms of their individual parts is important, because it enables a precise understanding of the objects' geometrical structure, and enhances object recogni…
Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model
Yihong Sun, Adam Kortylewski, Alan Yuille
Amodal completion is a visual task that humans perform easily but which is difficult for computer vision algorithms. The aim is to segment those object boundaries which are occlude…
CoKe: Localized Contrastive Learning for Robust Keypoint Detection
Yutong Bai, Angtian Wang, Adam Kortylewski +1
In this paper, we introduce a contrastive learning framework for keypoint detection (CoKe). Keypoint detection differs from other visual tasks where contrastive learning has been a…
Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition under Occlusion
Adam Kortylewski, Qing Liu, Angtian Wang +2
Computer vision systems in real-world applications need to be robust to partial occlusion while also being explainable. In this work, we show that black-box deep convolutional neur…
Robust Object Detection under Occlusion with Context-Aware CompositionalNets
Angtian Wang, Yihong Sun, Adam Kortylewski +1
Detecting partially occluded objects is a difficult task. Our experimental results show that deep learning approaches, such as Faster R-CNN, are not robust at object detection unde…
Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion
Adam Kortylewski, Ju He, Qing Liu +1
Recent findings show that deep convolutional neural networks (DCNNs) do not generalize well under partial occlusion. Inspired by the success of compositional models at classifying…
PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning
Chenglin Yang, Adam Kortylewski, Cihang Xie +2
Patch-based attacks introduce a perceptible but localized change to the input that induces misclassification. A limitation of current patch-based black-box attacks is that they per…