A survey on metric learning for feature vectors and structured data

A Bellet, A Habrard, M Sebban - arxiv preprint arxiv:1306.6709, 2013‏ - arxiv.org
The need for appropriate ways to measure the distance or similarity between data is
ubiquitous in machine learning, pattern recognition and data mining, but handcrafting such …

Multiple kernel learning for visual object recognition: A review

SS Bucak, R **, AK Jain - IEEE Transactions on Pattern …, 2013‏ - ieeexplore.ieee.org
Multiple kernel learning (MKL) is a principled approach for selecting and combining kernels
for a given recognition task. A number of studies have shown that MKL is a useful tool for …

Visual recognition with deep nearest centroids

W Wang, C Han, T Zhou, D Liu - arxiv preprint arxiv:2209.07383, 2022‏ - arxiv.org
We devise deep nearest centroids (DNC), a conceptually elegant yet surprisingly effective
network for large-scale visual recognition, by revisiting Nearest Centroids, one of the most …

Deep sets

M Zaheer, S Kottur, S Ravanbakhsh… - Advances in neural …, 2017‏ - proceedings.neurips.cc
We study the problem of designing models for machine learning tasks defined on sets. In
contrast to the traditional approach of operating on fixed dimensional vectors, we consider …

On the automatic generation of medical imaging reports

B **g, P **e, E **ng - arxiv preprint arxiv:1711.08195, 2017‏ - arxiv.org
Medical imaging is widely used in clinical practice for diagnosis and treatment. Report-
writing can be error-prone for unexperienced physicians, and time-consuming and tedious …

Deep learning for extreme multi-label text classification

J Liu, WC Chang, Y Wu, Y Yang - … of the 40th international ACM SIGIR …, 2017‏ - dl.acm.org
Extreme multi-label text classification (XMTC) refers to the problem of assigning to each
document its most relevant subset of class labels from an extremely large label collection …

Cnn-rnn: A unified framework for multi-label image classification

J Wang, Y Yang, J Mao, Z Huang… - Proceedings of the …, 2016‏ - openaccess.thecvf.com
While deep convolutional neural networks (CNNs) have shown a great success in single-
label image classification, it is important to note that most real world images contain multiple …

Learning fine-grained image similarity with deep ranking

J Wang, Y Song, T Leung… - Proceedings of the …, 2014‏ - openaccess.thecvf.com
Learning fine-grained image similarity is a challenging task. It needs to capture between-
class and within-class image differences. This paper proposes a deep ranking model that …

Hierarchy parsing for image captioning

T Yao, Y Pan, Y Li, T Mei - Proceedings of the IEEE/CVF …, 2019‏ - openaccess.thecvf.com
It is always well believed that parsing an image into constituent visual patterns would be
helpful for understanding and representing an image. Nevertheless, there has not been …

Is object localization for free?-weakly-supervised learning with convolutional neural networks

M Oquab, L Bottou, I Laptev… - Proceedings of the IEEE …, 2015‏ - openaccess.thecvf.com
Successful visual object recognition methods typically rely on training datasets containing
lots of richly annotated images. Annotating object bounding boxes is both expensive and …