Abstract We introduce the Segment Anything (SA) project: a new task, model, and dataset for
image segmentation. Using our efficient model in a data collection loop, we built the largest …

We present Segment Anything Model 2 (SAM 2), a foundation model towards solving
promptable visual segmentation in images and videos. We build a data engine, which …

X-ray imagery systems have enabled security personnel to identify potential threats
contained within the baggage and cargo since the early 1970s. However, the manual …

Adversarial attacks are valuable for evaluating the robustness of deep learning models.
Existing attacks are primarily conducted on the visible light spectrum (eg, pixel-wise texture …

X-ray imaging technology has been used for decades in clinical tasks to reveal the internal
condition of different organs, and in recent years, it has become more common in other …

While semantic segmentation has seen tremendous improvements in the past, there are still
significant labeling efforts necessary and the problem of limited generalization to classes …

Low-resource settings are well-established in natural lan-guage processing where many
languages lack sufficient data for deep learning at scale. However low-resource problems …

Existing cross-domain detection methods mostly study the domain shifts where differences
between domains are often caused by external environment and perceivable for humans …

Automatic security inspection relying on computer vision technology is a challenging task in
real-world scenarios due to many factors, such as intra-class variance, class imbalance, and …

X-ray baggage inspection automatically determines whether there are prohibited items in
passenger luggage and has recently achieved good progress due to the development of …