The deep learning-based image segmentation approach has evolved into the mainstream of
target detection and shape characterization in microscopic image analysis. However, the …

Adversarial attacks can easily fool object recognition systems based on deep neural
networks (DNNs). Although many defense methods have been proposed in recent years …

Unsupervised learning of keypoints and landmarks has seen significant progress with the
help of modern neural network architectures but performance is yet to match the supervised …

Deep learning for unsupervised image segmentation remains challenging due to the
absence of human labels. The common idea is to train a segmentation head, with the …

Motion, measured via optical flow, provides a powerful cue to discover and learn objects in
images and videos. However, compared to using appearance, it has some blind spots, such …

We introduce MOVE, a novel method to segment objects without any form of supervision.
MOVE exploits the fact that foreground objects can be shifted locally relative to their initial …

Supervised keypoint localization methods rely on large manually labeled image datasets,
where objects can deform, articulate, or occlude. However, creating such large keypoint …

Structured representations such as keypoints are widely used in pose transfer, conditional
image generation, animation, and 3D reconstruction. However, their supervised learning …

Landmark detection is a fundamental task aiming at identifying specific landmarks that serve
as representations of distinct object features within an image. However, the present …

The paper introduces PaintSeg, a new unsupervised method for segmenting objects without
any training. We propose an adversarial masked contrastive painting (AMCP) process …