Main Page
Computer Vision Student Seminars
The Computer Vision Student Seminars at the University of Maryland College Park are a student-run series of talks given by current graduate students for current graduate students.
To receive regular information about the Computer Vision Student Seminars, subscribe to our mailing list or our talks list.
Description[edit]
The purpose of these talks is to:
- Encourage interaction between computer vision students;
- Provide an opportunity for computer vision students to be aware of and possibly get involved in the research their peers are conducting;
- Provide an opportunity for computer vision students to receive feedback on their current research;
- Provide speaking opportunities for computer vision students.
The guidelines for the format are:
- An hour-long weekly meeting, consisting of one 20-40 minute talk followed by discussion and food.
- The talks are meant to be casual and discussion is encouraged.
- Topics may include current research, past research, general topic presentations, paper summaries and critiques, or anything else beneficial to the computer vision graduate student community.
Schedule Spring 2014[edit]
All talks take place on Thursdays at 3:30pm in AVW 3450.
| Date | Speaker | Title |
|---|---|---|
| October 16 | Abhishek Sharma | Recursive Context Propagation Network for Semantic Scene Labeling |
| October 23 | Ang Li | Planar Structure Matching Under Projective Uncertainty for Geolocation |
| October 30 | Cancelled | Cancelled |
| November 6 | Ejaz Ahmed | Knowing a Good HOG Filter When You See It: Efficient Selection of Filters for Detection |
| November 13 | CVPR deadline, no meeting | |
| November 20 | Kota Hara | Growing Regression Forests by Classification: Applications to Object Pose Estimation |
| November 27 | Thanksgiving break, no meeting | |
| December 4 | Angjoo Kanazawa | Locally Convolutional Neural Network |
| December 11 | Aleksandrs |
Talk Abstracts Fall 2014[edit]
Recursive Context Propagation Network for Semantic Scene Labeling[edit]
Speaker: Abhishek Sharma -- Date: October 16, 2014
Abstract: The talk will briefly touch upon the Multi-scale CNN of Lecun and Farabet to extract pixel-wise features for semantic segmentation and then I will move on to discuss the work we did to enhance the model further in order to result in a real-time and accurate pixel-wise labeling pipeline. I will talk about a deep feed-forward neural network architecture for pixel-wise semantic scene labeling. It uses a novel recursive neural network architecture for context propagation, referred to as rCPN. It first maps the local features into a semantic space followed by a bottom-up aggregation of local information into a global feature of the entire image. Then a top-down propagation of the aggregated information takes place that enhances the contextual information of each local features. Therefore, the information from every location in the image is propagated to every other location. Experimental results on Stanford background and SIFT Flow datasets show that the proposed method outperforms previous approaches in terms of accuracy. It is also orders of magnitude faster than previous methods and takes only 0.07 seconds on a GPU for pixel-wise labeling of a 256 by 256 image starting from raw RGB pixel values, given the super-pixel mask that takes an additional 0.3 seconds using an off-the-shelf implementation.
Planar Structure Matching Under Projective Uncertainty for Geolocation[edit]
Speaker: Ang Li -- Date: October 23, 2014
Abstract: Image based geolocation aims to answer the question: where was this ground photograph taken? We present an approach to geoloca- lating a single image based on matching human delineated line segments in the ground image to automatically detected line segments in ortho images. Our approach is based on distance transform matching. By ob- serving that the uncertainty of line segments is non-linearly amplified by projective transformations, we develop an uncertainty based repre- sentation and incorporate it into a geometric matching framework. We show that our approach is able to rule out a considerable portion of false candidate regions even in a database composed of geographic areas with similar visual appearances.
Knowing a Good HOG Filter When You See It: Efficient Selection of Filters for Detection[edit]
Speaker: Ejaz Ahmed -- Date: November 6, 2014
Abstract: Collections of filters based on histograms of oriented gradients (HOG) are common for several detection methods, notably, poselets and exemplar SVMs. The main bottleneck in training such systems is the selection of a subset of good filters from a large number of possible choices. We show that one can learn a universal model of part “goodness” based on properties that can be computed from the filter itself. The intuition is that good filters across categories exhibit common traits such as, low clutter and gradients that are spatially correlated. This allows us to quickly discard filters that are not promising thereby speeding up the training procedure. Applied to training the poselet model, our automated selection procedure allows us to improve its detection performance on the PASCAL VOC data sets, while speeding up training by an order of magnitude. Similar results are reported for exemplar SVMs.
Growing Regression Forests by Classification: Applications to Object Pose Estimation[edit]
Speaker: Kota Hara -- Date: November 20, 2014
Abstract: In this work, we propose a novel node splitting method for regression trees and incorporate it into the regression forest framework. Unlike traditional binary splitting, where the splitting rule is selected from a predefined set of binary splitting rules via trial-and-error, the proposed node splitting method first finds clusters of the training data which at least locally minimize the empirical loss without considering the input space. Then splitting rules which preserve the found clusters as much as possible are determined by casting the problem into a classification problem. Consequently, our new node splitting method enjoys more freedom in choosing the splitting rules, resulting in more efficient tree structures. In addition to the Euclidean target space, we present a variant which can naturally deal with a circular target space by the proper use of circular statistics. We apply the regression forest employing our node splitting to head pose estimation (Euclidean target space) and car direction estimation (circular target space) and demonstrate that the proposed method significantly outperforms state-of-the-art methods (38.5\% and 22.5\% error reduction respectively).
Locally Convolutional Neural Network[edit]
Speaker: Angjoo Kanazawa -- Date: December 4, 2014
Abstract: Convolutional Neural Networks (ConvNets) have shown excellent results on many visual classification tasks. With the exception of ImageNet, these datasets are carefully crafted such that objects are well-aligned at similar scales. Naturally, the feature learning problem gets more challenging as the amount of variation in the data increases, as the models have to learn to be invariant to certain changes in appearance. Recent results on the ImageNet dataset show that given enough data, ConvNets can learn such invariances producing very discriminative features [1]. But could we do more: use less parameters, less data, learn more discriminative features, if certain invariances were built into the learning process? In this paper we present a simple model that allows ConvNets to learn features in a locally scale-invariant manner without increasing the number of model parameters. We show on a modified MNIST dataset that when faced with scale variation, building in scale-invariance allows ConvNets to learn more discriminative features with reduced chances of over-fitting.
Past Semesters[edit]
Funded By[edit]
- Computer Vision Faculty
- Northrop Grumman
Current Seminar Series Coordinators[edit]
Emails are at umiacs.umd.edu.
| Jonghyun Choi, jhchoi@ | (student of Professor Larry Davis) |
| Austin Myers, amyers@ | (student of Professor Yiannis Aloimonos) |
| Raviteja Vemulapalli, raviteja @ | (student of Professor Rama Chellappa) |
Gone but not forgotten.
| Angjoo Kanazawa | |
| Sameh Khamis | |
| Ejaz Ahmed | |
| Anne Jorstad | now at EPFL |
| Jie Ni | off this semester |
| Sima Taheri | |
| Ching Lik Teo |
