Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userIdentity Preserve Transform: Understand What Activity Classification Models Have Learnt
67
0
0.0
(
0
)
Added by
Jialing Lyu
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Activity classification has observed great success recently. The performance on small dataset is almost saturated and people are moving towards larger datasets. What leads to the performance gain on the model and what the model has learnt? In this paper we propose identity preserve transform (IPT) to study this problem. IPT manipulates the nuisance factors (background, viewpoint, etc.) of the data while keeping those factors related to the task (human motion) unchanged. To our surprise, we found popular models are using highly correlated information (background, object) to achieve high classification accuracy, rather than using the essential information (human motion). This can explain why an activity classification model usually fails to generalize to datasets it is not trained on. We implement IPT in two forms, i.e. image-space transform and 3D transform, using synthetic images. The tool will be made open-source to help study model and dataset design.
rate research
Read More
We review the main results obtained from our seismic studies of B-type main sequence pulsators, based on the ground-based, MOST, Kepler and BRITE observations. Important constraints on stellar opacities, convective overshooting and rotation are derived. In each studied case, a significant modification of the opacity profile at the depths corresponding to the temperature range $log{T}in (5.0-5.5)$ is indispensable to explain all pulsational properties. In particular, a huge amount of opacity (at least 200%) at the depth of the temperature $log T = 5.46$ (the nickel opacity) has to be added in early B-type stellar models to account for low frequencies which correspond to high-order g modes. The values of the overshooting parameter, $alpha_{rm ov}$, from our seismic studies is below 0.3. In the case of a few stars, the deeper interiors have to rotate faster to get the g-mode instability in the whole observed range.
This document will review the most prominent proposals using multilayer convolutional architectures. Importantly, the various components of a typical convolutional network will be discussed through a review of different approaches that base their design decisions on biological findings and/or sound theoretical bases. In addition, the different attempts at understanding ConvNets via visualizations and empirical studies will be reviewed. The ultimate goal is to shed light on the role of each layer of processing involved in a ConvNet architecture, distill what we currently understand about ConvNets and highlight critical open problems.
As the success of deep models has led to their deployment in all areas of computer vision, it is increasingly important to understand how these representations work and what they are capturing. In this paper, we shed light on deep spatiotemporal representations by visualizing what two-stream models have learned in order to recognize actions in video. We show that local detectors for appearance and motion objects arise to form distributed representations for recognizing human actions. Key observations include the following. First, cross-stream fusion enables the learning of true spatiotemporal features rather than simply separate appearance and motion features. Second, the networks can learn local representations that are highly class specific, but also generic representations that can serve a range of classes. Third, throughout the hierarchy of the network, features become more abstract and show increasing invariance to aspects of the data that are unimportant to desired distinctions (e.g. motion patterns across various speeds). Fourth, visualizations can be used not only to shed light on learned representations, but also to reveal idiosyncracies of training data and to explain failure cases of the system.
Image manipulation with natural language, which aims to manipulate images with the guidance of language descriptions, has been a challenging problem in the fields of computer vision and natural language processing (NLP). Currently, a number of efforts have been made for this task, but their performances are still distant away from generating realistic and text-conformed manipulated images. Therefore, in this paper, we propose a memory-based Image Manipulation Network (MIM-Net), where a set of memories learned from images is introduced to synthesize the texture information with the guidance of the textual description. We propose a two-stage network with an additional reconstruction stage to learn the latent memories efficiently. To avoid the unnecessary background changes, we propose a Target Localization Unit (TLU) to focus on the manipulation of the region mentioned by the text. Moreover, to learn a robust memory, we further propose a novel randomized memory training loss. Experiments on the four popular datasets show the better performance of our method compared to the existing ones.
We summarize our current understanding of the neutrino flavor
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
