[AI Seminar] ai-seminar-announce Digest, Vol 77, Issue 4

Adams Wei Yu weiyu at cs.cmu.edu
Mon Oct 16 08:05:15 EDT 2017

A gentle reminder that the talk will happen tomorrow (Tuesday) noon at NSH

On Sat, Oct 14, 2017 at 9:00 AM, <ai-seminar-announce-request at cs.cmu.edu>

> Send ai-seminar-announce mailing list submissions to
>         ai-seminar-announce at cs.cmu.edu
> To subscribe or unsubscribe via the World Wide Web, visit
>         https://mailman.srv.cs.cmu.edu/mailman/listinfo/ai-
> seminar-announce
> or, via email, send a message with subject or body 'help' to
>         ai-seminar-announce-request at cs.cmu.edu
> You can reach the person managing the list at
>         ai-seminar-announce-owner at cs.cmu.edu
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of ai-seminar-announce digest..."
> Today's Topics:
>    1.  AI Seminar sponsored by Apple -- Xiaolong Wang --        October 17
>       (Adams Wei Yu)
> ----------------------------------------------------------------------
> Message: 1
> Date: Sat, 14 Oct 2017 05:32:34 -0700
> From: Adams Wei Yu <weiyu at cs.cmu.edu>
> To: ai-seminar-announce at cs.cmu.edu
> Subject: [AI Seminar] AI Seminar sponsored by Apple -- Xiaolong Wang
>         --      October 17
> Message-ID:
>         <CABzq7epRGZ8vK1qBjUomXKynJDyD=WS2caQeNeaYLEiDBrB86w at mail.
> gmail.com>
> Content-Type: text/plain; charset="utf-8"
> Dear faculty and students,
> We look forward to seeing you next Tuesday, October 17, at noon in NSH 3305
> for AI Seminar sponsored by Apple. To learn more about the seminar series,
> please visit the AI Seminar webpage <http://www.cs.cmu.edu/~aiseminar/>.
> On Tuesday, Xiaolong Wang <http://www.cs.cmu.edu/~xiaolonw/> will give the
> following talk:
> Title:  Learning Visual Representations for Object Detection
> Abstract:
> Object detection is in the center of applications in computer vision. The
> current pipeline for training object detectors include ConvNet pre-training
> and fine-tuning. In this talk, I am going to cover our works on
> self-supervised/unsupervised ConvNet pre-training as well as optimization
> strategies on fine-tuning.
> For ConvNet pre-training, instead of using millions of labeled images, we
> explored to learn visual representations using supervisions from the data
> itself without any human labels, i.e., self-supervised learning.
> Specifically, we proposed 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).
> Instead of combining two approaches with multi-task learning, we organized
> the data with multiple variations in a graph and applied simple transitive
> rules to generate pairs of images with richer visual invariance for
> training. This approach brings the object detection accuracies on MSCOCO
> dataset less than 1% away from methods using large amount of labeled data
> (e.g., ImageNet).
> For object detection fine-tuning, we proposed to train object detectors
> invariant to occlusions and deformations. The common solution is to use a
> data-driven strategy -- collect large-scale datasets which have object
> instances under different conditions. However, like categories, occlusions
> and object deformations also follow a long-tail. Some occlusions and
> deformations are so rare that they hardly happen; yet we want to learn a
> model invariant to such occurrences. In this talk, we propose to learn an
> adversarial network that generates examples with occlusions and
> deformations. The goal of the adversary is to generate examples that are
> difficult for the object detector to classify. In our framework both the
> original detector and adversary are learned in a joint manner. We show
> significant improvements on different datasets (VOC, COCO) with different
> network architectures (AlexNet, VGG16, ResNet101).
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-
> announce/attachments/20171014/763f531f/attachment-0001.html>
> ------------------------------
> Subject: Digest Footer
> _______________________________________________
> ai-seminar-announce mailing list
> ai-seminar-announce at cs.cmu.edu
> https://mailman.srv.cs.cmu.edu/mailman/listinfo/ai-seminar-announce
> ------------------------------
> End of ai-seminar-announce Digest, Vol 77, Issue 4
> **************************************************
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20171016/dd9578f1/attachment.html>

More information about the ai-seminar-announce mailing list