Supplementary Material — Beyond Spatial Pooling: Fine-Grained Representation Learning in Multiple Domains
نویسندگان
چکیده
This supplementary material is organized as follows. Sec. 2.1 and Sec. 2.2 present proofs for the Eq. 4 in the paper in the case of max and average pooling operator, respectively. Sec. 2.3 substantiates variance statements associated with Eq. 6 and Eq. 7 in the Section 3.3. Sec. 3 shows numerical details for Fig. 4 and Fig. 5 in the paper. Last, Sec. 4 shows examples of object instances in JHUIT-50 dataset. Additionally, it shows a subset of training and testing samples to illustrate the experiment setting applied in JHUIT-50.
منابع مشابه
Where to Focus: Deep Attention-based Spatially Recurrent Bilinear Networks for Fine-Grained Visual Recognition
Fine-grained visual recognition typically depends on modeling subtle difference from object parts. However, these parts often exhibit dramatic visual variations such as occlusions, viewpoints, and spatial transformations, making it hard to detect. In this paper, we present a novel attention-based model to automatically, selectively and accurately focus on critical object regions with higher imp...
متن کاملSimilar exemplar pooling processes underlie the learning of facial identity and handwriting style: Evidence from typical observers and individuals with Autism.
Considerable research has addressed whether the cognitive and neural representations recruited by faces are similar to those engaged by other types of visual stimuli. For example, research has examined the extent to which objects of expertise recruit holistic representation and engage the fusiform face area. Little is known, however, about the domain-specificity of the exemplar pooling processe...
متن کاملSupplementary material of the CVPR’17 Viraliency: Pooling Local Virality
We implemented our LENA pooling layer within the Caffe framework and ran all our experiments using a Tesla K40 GPU. All the networks were fine-tuned from the convolutional filters obtained when training these networks for the 1,000 image classification task on the ImageNet dataset. We iterated the stochastic gradient descent algorithm for 10,000 iterations with a momentum of μ = 0.9 and a weigh...
متن کاملImage Classification via Sparse Representation and Subspace Alignment
Image representation is a crucial problem in image processing where there exist many low-level representations of image, i.e., SIFT, HOG and so on. But there is a missing link across low-level and high-level semantic representations. In fact, traditional machine learning approaches, e.g., non-negative matrix factorization, sparse representation and principle component analysis are employed to d...
متن کاملFine-grained sketch-based image retrieval by matching deformable part models
An important characteristic of sketches, compared with text, rests with their ability to intrinsically capture object appearance and structure. Nonetheless, akin to traditional text-based image retrieval, conventional sketch-based image retrieval (SBIR) principally focuses on retrieving images of the same category, neglecting the fine-grained characteristics of sketches. In this paper, we advoc...
متن کامل