Interpreting Deep Visual Representations via Network Dissection
نویسندگان
چکیده
منابع مشابه
Interpreting Deep Visual Representations via Network Dissection
The success of recent deep convolutional neural networks (CNNs) depends on learning hidden representations that can summarize the important factors of variation behind the data. However, CNNs often criticized as being black boxes that lack interpretability, since they have millions of unexplained model parameters. In this work, we describe Network Dissection, a method that interprets networks b...
متن کاملInterpreting genomic data via entropic dissection
Since the emergence of high-throughput genome sequencing platforms and more recently the next-generation platforms, the genome databases are growing at an astronomical rate. Tremendous efforts have been invested in recent years in understanding intriguing complexities beneath the vast ocean of genomic data. This is apparent in the spurt of computational methods for interpreting these data in th...
متن کاملBetter Mixing via Deep Representations
It has been hypothesized, and supported with experimental evidence, that deeper representations, when well trained, tend to do a better job at disentangling the underlying factors of variation. We study the following related conjecture: better representations, in the sense of better disentangling, can be exploited to produce Markov chains that mix faster between modes. Consequently, mixing betw...
متن کاملVisual Representations: Defining Properties and Deep Approximations
Visual representations are defined in terms of minimal sufficient statistics of visual data, for a class of tasks, that are also invariant to nuisance variability. Minimal sufficiency guarantees that we can store a representation in lieu of raw data with smallest complexity and no performance loss on the task at hand. Invariance guarantees that the statistic is constant with respect to uninform...
متن کاملExtracting Visual Patterns from Deep Learning Representations
Vector-space word representations based on neural network models can include linguistic regularities, enabling semantic operations based on vector arithmetic. In this paper, we explore an analogous approach applied to images. We define a methodology to obtain large and sparse vectors from individual images and image classes, by using a pre-trained model of the GoogLeNet architecture. We evaluat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Pattern Analysis and Machine Intelligence
سال: 2019
ISSN: 0162-8828,2160-9292,1939-3539
DOI: 10.1109/tpami.2018.2858759