Sorry, you need to enable JavaScript to visit this website.

Cross-validation under sample selection bias can, in principle, be done by importance-weighting the empirical risk. However, the importance-weighted risk estimator produces sub-optimal hyperparameter estimates in problem settings where large weights arise with high probability. We study its sampling variance as a function of the training data distribution and introduce a control variate to increase its robustness to problematically large weights.

While data poisoning attacks on classifiers were originally proposed to degrade a classifier's usability, there has been strong recent interest in backdoor data poisoning attacks, where the classifier learns to classify to a target class whenever a backdoor pattern ({\it e.g.}, a watermark or innocuous pattern) is added to an example from some class other than the target class.

One of the key challenges of deep learning based image retrieval remains in aggregating convolutional activations into one highly representative feature vector. Ideally, this descriptor should encode semantic, spatial and low level information. Even though off-the-shelf pre-trained neural networks can already produce good representations in combination with aggregation methods, appropriate fine tuning for the task of image retrieval has shown to significantly boost retrieval performance.

Image-based people counting is a challenging work due to the large scale variation problem caused by the diversity of distance between the camera and the person, especially in the congested scenes. To handle this problem, the previous methods focus on building complicated models and rely on labeling the sophisticated density maps to learn the scale variation implicitly. It is often time-consuming in data pre-processing and difficult to train these deep models due to the lack of training data.

We present an approach to synthesize highly photorealistic images of 3D object models, which we use to train a convolutional neural network for detecting the objects in real images. The proposed approach has three key ingredients: (1) 3D object models are rendered in 3D models of complete scenes with realistic materials and lighting, (2) plausible geometric configuration of objects and cameras in a scene is generated using physics simulation, and (3) high photorealism of the synthesized images is achieved by physically based rendering.

With the development of deep learning, many state-of-the-art natural image scene classification methods have demonstrated impressive performance. While the current convolution neural network tends to extract global features and global semantic information in a scene, the geo-spatial objects can be located at anywhere in an aerial image scene and their spatial arrangement tends to be more complicated. One possible solution is to preserve more local semantic information and enhance feature propagation.

Performance of 6DoF pose estimation techniques from RGB/RGB-D images has improved significantly with sophisticated deep learning frameworks. These frameworks require large-scale training data based on real/synthetic RGB/RGB-D information. Difficulty of obtaining adequate training data has limited the scope of these frameworks for ubiquitous application areas. Also, fast pose estimation at inference time often requires high-end GPU(s) that restricts the scope for its application in mobile hardware.

Current face detection concentrates on detecting tiny faces and severely occluded faces. Face analysis methods, however, require a good localization and would benefit greatly from some rotation information. We propose to predict a face direction vector (FDV), which provides the face size and orientation and can be learned by a common object detection architecture better than the traditional bounding box. It provides a more consistent definition of face location and size. Using the FDV is promising for all succeeding face analysis methods.