• Publications
  • Influence
Indoor Segmentation and Support Inference from RGBD Images
TLDR
The goal is to parse typical, often messy, indoor scenes into floor, walls, supporting surfaces, and object regions, and to recover support relationships, to better understand how 3D cues can best inform a structured 3D interpretation.
Learning without Forgetting
TLDR
This work proposes the Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities, and performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques.
Describing objects by their attributes
TLDR
This paper proposes to shift the goal of recognition from naming to describing, and introduces a novel feature selection method for learning attributes that generalize well across categories.
Recovering Surface Layout from an Image
TLDR
This paper takes the first step towards constructing the surface layout, a labeling of the image intogeometric classes, to learn appearance-based models of these geometric classes, which coarsely describe the 3D scene orientation of each image region.
Recovering the spatial layout of cluttered rooms
TLDR
This paper introduces a structured learning algorithm that chooses the set of parameters to minimize error, based on global perspective cues, and gains robustness to clutter by modeling the global room space with a parameteric 3D “box” and by iteratively localizing clutter and refitting the box.
Category Independent Object Proposals
TLDR
A category-independent method to produce a bag of regions and rank them, such that top-ranked regions are likely to be good segmentations of different objects, and the ability to find most objects within a small bag of proposed regions is demonstrated.
Diagnosing Error in Object Detectors
TLDR
This paper shows how to analyze the influences of object characteristics on detection performance and the frequency and impact of different types of false positives, and shows that sensitivity to size, localization error, and confusion with similar objects are the most impactful forms of error.
Geometric context from a single image
TLDR
This work shows that it can estimate the coarse geometric properties of a scene by learning appearance-based models of geometric classes, even in cluttered natural scenes, and provides a multiple-hypothesis framework for robustly estimating scene structure from a single image and obtaining confidences for each geometric label.
Single-image shadow detection and removal using paired regions
TLDR
This paper addressed the problem of shadow detection and removal from single images of natural scenes by employing a region based approach, and created a new dataset with shadow-free ground truth images, which provides a quantitative basis for evaluating shadow removal.
Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion
TLDR
DeepInversion is introduced, a new method for synthesizing images from the image distribution used to train a deep neural network, which optimizes the input while regularizing the distribution of intermediate feature maps using information stored in the batch normalization layers of the teacher.
...
...