Related papers: Unsupervised Vehicle Re-Identification via Self-su…

Sophisticated automatic incident detection (AID) technology plays a key role in contemporary transportation systems. Though many papers were devoted to study incident classification algorithms, few study investigated how to enhance feature…

Recognizing and disentangling visual attributes from objects is a foundation to many computer vision applications. While large vision language representations like CLIP had largely resolved the task of zero-shot object recognition,…

There exist many high-dimensional data in real-world applications such as biology, computer vision, and social networks. Feature selection approaches are devised to confront with high-dimensional data challenges with the aim of efficient…

Most existing person re-identification (re-id) methods require supervised model learning from a separate large set of pairwise labelled training data for every single camera pair. This significantly limits their scalability and usability in…

Nowadays, supervised deep learning techniques yield the best state-of-the-art prediction performances for a wide variety of computer vision tasks. However, such supervised techniques generally require a large amount of manually labeled…

Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models. However, existing methods simply utilize pseudo labels from clustering for…

In this paper we tackle the problem of vehicle re-identification in a camera network utilizing triplet embeddings. Re-identification is the problem of matching appearances of objects across different cameras. With the proliferation of…

Supervised learning of convolutional neural networks (CNNs) can require very large amounts of labeled data. Labeling thousands or millions of training examples can be extremely time consuming and costly. One direction towards addressing…

High-dimensional data is commonly encountered in numerous data analysis tasks. Feature selection techniques aim to identify the most representative features from the original high-dimensional data. Due to the absence of class label…

Existing public person Re-Identification~(ReID) datasets are small in modern terms because of labeling difficulty. Although unlabeled surveillance video is abundant and relatively easy to obtain, it is unclear how to leverage these footage…

We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves…

Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data. Unsupervised Domain Adaptation (UDA) is a promising approach to adapt models for new…

Given a small set of labeled data and a large set of unlabeled data, semi-supervised learning (SSL) attempts to leverage the location of the unlabeled datapoints in order to create a better classifier than could be obtained from supervised…

Fine-grained image classification involves identifying different subcategories of a class which possess very subtle discriminatory features. Fine-grained datasets usually provide bounding box annotations along with class labels to aid the…

As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for…

Visual localization is a crucial problem in mobile robotics and autonomous driving. One solution is to retrieve images with known pose from a database for the localization of query images. However, in environments with drastically varying…

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…

Semi-supervised anomaly detection, which aims to improve the anomaly detection performance by using a small amount of labeled anomaly data in addition to unlabeled data, has attracted attention. Existing semi-supervised approaches assume…

Supervised deep learning-based hash and vector quantization are enabling fast and large-scale image retrieval systems. By fully exploiting label annotations, they are achieving outstanding retrieval performances compared to the conventional…

The goal of domain generalization is to learn from multiple source domains to generalize to unseen target domains under distribution discrepancy. Current state-of-the-art methods in this area are fully supervised, but for many real-world…