Research Area
Year Published

203 Results

October 22, 2017

Predicting Deeper into the Future of Semantic Segmentation

International Conference on Computer Vision (ICCV)

The ability to predict and therefore to anticipate the future is an important attribute of intelligence. We introduce the novel task of predicting semantic segmentations of future frames. Given a sequence of video frames, our goal is to predict segmentation maps of not yet observed video frames that lie up to a second or further in the future.

By: Pauline Luc, Natalia Neverova, Camille Couprie, Jakob Verbeek, Yann LeCun

October 22, 2017

Inferring and Executing Programs for Visual Reasoning

International Conference on Computer Vision (ICCV)

Inspired by module networks, this paper proposes a model for visual reasoning that consists of a program generator that constructs an explicit representation of the reasoning process to be performed, and an execution engine that executes the resulting program to produce an answer.

By: Justin Johnson, Bharath Hariharan, Laurens van der Maaten, Judy Hoffman, Li Fei-Fei, Larry Zitnick, Ross Girshick

October 22, 2017

Low-shot Visual Recognition by Shrinking and Hallucinating Features

International Conference on Computer Vision (ICCV)

Low-shot visual learning—the ability to recognize novel object categories from very few examples—is a hallmark of human visual intelligence. Existing machine learning approaches fail to generalize in the same way. We present a lowshot learning benchmark on complex images that mimics challenges faced by recognition systems in the wild.

By: Bharath Hariharan, Ross Girshick

October 22, 2017

Focal Loss for Dense Object Detection

International Conference on Computer Vision (ICCV)

In this paper, we investigate why one-stage detectors that are applied over a regular, dense sampling of possible object locations have the potential to be faster and simpler, but have trailed the accuracy of two-stage detectors thus far. We design and train a simple dense detector we call RetinaNet. Our results show that when trained with the focal loss, RetinaNet is able to match the speed of previous one-stage detectors while surpassing the accuracy of all existing state-of-the-art two-stage detectors.

By: Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, Piotr Dollar

October 22, 2017

Deltille Grids for Geometric Camera Calibration

International Conference on Computer Vision (ICCV)

The recent proliferation of high resolution cameras presents an opportunity to achieve unprecedented levels of precision in visual 3D reconstruction. Yet the camera calibration pipeline, developed decades ago using checkerboards, has remained the de facto standard. In this paper, we ask the question: are checkerboards the optimal pattern for high precision calibration?

By: Hyowon Ha, Michal Perdoch, Hatem Alismail, In So Kweon, Yaser Sheikh

October 22, 2017

Mask R-CNN

International Conference on Computer Vision (ICCV)

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The method, called Mask R-CNN, extends Faster R-CNN by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition.

By: Kaiming He, Georgia Gkioxari, Piotr Dollar, Ross Girshick

October 22, 2017

Transitive Invariance for Self-supervised Visual Representation Learning

International Conference on Computer Vision (ICCV)

In this paper, we propose to exploit different self-supervised approaches to learn representations invariant to (i) inter-instance variations (two objects in the same class should have similar features) and (ii) intra-instance variations (viewpoint, pose, deformations, illumination, etc.).

By: Xiaolong Wang*, Kaiming He, Abhinav Gupta

October 22, 2017

Unsupervised Creation of Parameterized Avatars

International Conference on Computer Vision (ICCV)

We study the problem of mapping an input image to a tied pair consisting of a vector of parameters and an image that is created using a graphical engine from the vector of parameters. The mapping’s objective is to have the output image as similar as possible to the input image.

By: Lior Wolf, Yaniv Taigman, Adam Polyak

September 7, 2017

Natural Language Does Not Emerge ‘Naturally’ in Multi-Agent Dialog

Conference on Empirical Methods in Natural Language Processing (EMNLP)

In this paper, using a Task & Talk reference game between two agents as a testbed, we present a sequence of ‘negative’ results culminating in a ‘positive’ one – showing that while most agent-invented languages are effective (i.e. achieve near-perfect task rewards), they are decidedly not interpretable or compositional.

By: Satwik Kottur, José M.F. Moura, Stefan Lee, Dhruv Batra

September 4, 2017

Video Segmentation with Background Motion Models

British Machine Vision Conference (BMVC)

In this paper, we explore the idea of explicitly fitting more general motion models in order to classify trajectories as foreground or background. We find that homographies are sufficient to model a wide variety of background motions found in real-world videos.

By: Scott Wehrwein, Richard Szeliski