Deep Domain Confusion: Maximizing for Domain Invariance
نویسندگان
چکیده
Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark. Fine-tuning deep models in a new domain can require a significant amount of data, which for many applications is simply not available. We propose a new CNN architecture which introduces an adaptation layer and an additional domain confusion loss, to learn a representation that is both semantically meaningful and domain invariant. We additionally show that a domain confusion metric can be used for model selection to determine the dimension of an adaptation layer and the best position for the layer in the CNN architecture. Our proposed adaptation method offers empirical performance which exceeds previously published results on a standard benchmark visual domain adaptation task.
منابع مشابه
Deep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملIdentification of mineralization features and deep geochemical anomalies using a new FT-PCA approach
The analysis of geochemical data in frequency domain, as indicated in this research study, can provide new exploratory informationthat may not be exposed in spatial domain. To identify deep geochemical anomalies, sulfide zone and geochemical noises in Dalli Cu–Au porphyry deposit, a new approach based on coupling Fourier transform (FT) and principal component analysis (PCA) has beenused. The re...
متن کاملEXISTENCE OF A STEADY FLOW WITH A BOUNDED VORTEX IN AN UNBOUNDED DOMAIN
We prove the existence of steady 2-dimensional flows, containing a bounded vortex, and approaching a uniform flow at infinity. The data prescribed is the rearrangement class of the vorticity field. The corresponding stream function satisfies a semilinear elliptic partial differential equation. The result is proved by maximizing the kinetic energy over all flows whose vorticity fields are rearra...
متن کاملDeep Learning for Target Classification from SAR Imagery: Data Augmentation and Translation Invariance
This report deals with translation invariance of convolutional neural networks (CNNs) for automatic target recognition (ATR) from synthetic aperture radar (SAR) imagery. In particular, the translation invariance of CNNs for SAR ATR represents the robustness against misalignment of target chips extracted from SAR images. To understand the translation invariance of the CNNs, we trained CNNs which...
متن کاملAdversarial Multi-Task Learning of Deep Neural Networks for Robust Speech Recognition
A method of learning deep neural networks (DNNs) for noise robust speech recognition is proposed. It is widely known that representations (activations) of well-trained DNNs are highly invariant to noise, especially in higher layers, and such invariance leads to the noise robustness of DNNs. However, little is known about how to enhance such invariance of representations, which is a key for impr...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1412.3474 شماره
صفحات -
تاریخ انتشار 2014