Automatic diabetic retinopathy (DR) lesions segmentation makes great sense of assisting ophthalmologists in diagnosis.
In practice, however, biased samples with corrupted labels and of tailed classes commonly co-exist in training data.
Fine-grained geometry, captured by aggregation of point features in local regions, is crucial for object recognition and scene understanding in point clouds.
Through experiments we find that, without regression, the performance could be equally promising as long as we delicately design the network to suit the training objective.
The 2nd Anti-UAV Workshop \& Challenge aims to encourage research in developing novel and accurate methods for multi-scale object tracking.
Offline Siamese networks have achieved very promising tracking performance, especially in accuracy and efficiency.
Specifically, the constructed temporal relation graph explicitly builds connections between semantically related temporal features to model temporal relations between both adjacent and non-adjacent time steps.
In this paper, we introduce Attribute-conditioned Layout GAN to incorporate the attributes of design elements for graphic layout generation by forcing both the generator and the discriminator to meet attribute conditions.
The performance of 3D object detection models over point clouds highly depends on their capability of modeling local geometric patterns.
Specifically, iFAN achieves an overall F-score of 91. 15% on the Helen dataset for face parsing, a normalized mean error of 5. 81% on the MTFL dataset for facial landmark localization and an accuracy of 45. 73% on the BNU dataset for emotion recognition with a single model.
In this work, we present a simple, highly efficient and modularized Dual Path Network (DPN) for image classification which presents a new topology of connection paths internally.
In this work, we address the small object detection problem by developing a single architecture that internally lifts representations of small objects to "super-resolved" ones, achieving similar characteristics as large objects and thus more discriminative for detection.
Most of existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately.
We provide preliminary answers to these questions through developing a novel Attention to Context Convolution Neural Network (AC-CNN) based object detection model.
Video object detection is challenging because objects that are easily detected in one frame may be difficult to detect in another frame within the same clip.
Taking pedestrian detection as an example, we illustrate how we can leverage this philosophy to develop a Scale-Aware Fast R-CNN (SAF R-CNN) framework.
Ranked #21 on Pedestrian Detection on Caltech