Today's deep learning methods focus on how to design the objective functions to make the
prediction as close as possible to the target. Meanwhile, an appropriate neural network …

Real-time object detection is one of the most important research topics in computer vision.
As new approaches regarding architecture optimization and training optimization are …

Modern detection transformers (DETRs) use a set of object queries to predict a list of
bounding boxes, sort them by their classification confidence scores, and select the top …

Prevalent state-of-the-art instance segmentation methods fall into a query-based scheme, in
which instance masks are derived by querying the image feature using a set of instance …

Two-stage and query-based instance segmentation methods have achieved remarkable
results. However, their segmented masks are still very coarse. In this paper, we present …

Deep learning-based object detection is a fundamental but challenging problem in computer
vision field, has attracted a lot of study in recent years. State-of-the-art object detection …

Large-scale object detection and instance segmentation face a severe data imbalance. The
finer-grained object classes become, the less frequent they appear in our datasets …

Large vocabulary object detectors are often faced with the long-tailed label distributions,
seriously degrading their ability to detect rarely seen categories. On one hand, the rare …

Person re-identification (re-ID) is commonly investigated as a ranking problem. However, the
performance of existing re-ID models drops dramatically, when they encounter extreme …

Deep object detectors suffer from the gradient contribution imbalance during training. In this
paper, we point out that such imbalance can be ascribed to the imbalance in example …