“We're feeding them through a deep neural network and using the activations of an intermediate layer as an embedding. You can read more about this technique in https://arxiv.org/abs/1403.6382 if you're interested.”
CNN Features off-the-shelf: an Astounding Baseline for Recognition
Recent results indicate that the generic descriptors extracted from the convolutional neural networks are very powerful. This paper adds to the mounting evidence that this is indeed the case. We report on a series of experiments conducted for different recognition tasks using the publicly available code and model of the \overfeat network which was trained to perform object classification on ILSVRC13. We use features extracted from the \overfeat network as a generic image representation to tackle the diverse range of recognition tasks of object image classification, scene recognition, fine grained recognition, attribute detection and image retrieval applied to a diverse set of datasets. We selected these tasks and datasets as they gradually move further away from the original task and data the \overfeat network was trained to solve. Astonishingly, we report consistent superior results compared to the highly tuned state-of-the-art systems in all the visual classification tasks on various datasets. For instance retrieval it consistently outperforms low memory footprint methods except for sculptures dataset. The results are achieved using a linear SVM classifier (or $L2$ distance in case of retrieval) applied to a feature representation of size 4096 extracted from a layer in the net. The representations are further modified using simple augmentation techniques e.g. jittering. The results strongly suggest that features obtained from deep learning with convolutional nets should be the primary candidate in most visual recognition tasks.
候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。
HN 书评
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“Hey! We're embedding images by feeding them through a deep neural net and using the activations of an intermediate layer as an embedding. You can read https://arxiv.org/abs/1403.6382 to learn more about this technique if you're interested. Our launch model is trained on ImageNet, which has enough variety that it usually generalizes well even when your …”
“> Is it always good enough to take the outputs of the next-to-last layer as features? It usually doesn't matter all that much whether you take the next-to-last or the third from last, it all performs pretty similarly. If you're doing transfer to a task that's very dissimilar from the pretraining task, I think it can sometimes be helpful to take the first…”
- ConvNet Features off-the-shelf: an Astounding Baseline for Object Recognition ↗m_ke · 2014-04-04 · 10 分