Related papers: Large-Scale Evaluation of Open-Set Image Classific…

We present an open-set logo detection (OSLD) system, which can detect (localize and recognize) any number of unseen logo classes without re-training; it only requires a small set of canonical logo images for each logo class. We achieve this…

We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i.e. classifying instances among a set of classes for which we only have a few labeled samples, while simultaneously detecting instances that do not belong to any known class. We…

Zero-Shot Learning (ZSL) focuses on classifying samples of unseen classes with only their side semantic information presented during training. It cannot handle real-life, open-world scenarios where there are test samples of unknown classes…

Unlabeled data is often abundant in the clinic, making machine learning methods based on semi-supervised learning a good match for this setting. Despite this, they are currently receiving relatively little attention in medical image…

Open-set recognition generalizes a classification task by classifying test samples as one of the known classes from training or "unknown." As novel cancer drug cocktails with improved treatment are continually discovered, predicting cancer…

Food recognition models often struggle to distinguish between seen and unseen samples, frequently misclassifying samples from unseen categories by assigning them an in-distribution (ID) label. This misclassification presents significant…

As the Internet is growing rapidly these years, the variant of malicious software, which often referred to as malware, has become one of the major and serious threats to Internet users. The dramatic increase of malware has led to a research…

Nowadays, with the advance of technology, there is an increasing amount of unstructured data being generated every day. However, it is a painful job to label and organize it. Labeling is an expensive, time-consuming, and difficult task. It…

This paper proposes to go beyond the state-of-the-art deep convolutional neural network (CNN) by incorporating the information from object detection, focusing on dealing with fine-grained image classification. Unfortunately, CNN suffers…

Current closed-set instance segmentation models rely on pre-defined class labels for each mask during training and evaluation, largely limiting their ability to detect novel objects. Open-world instance segmentation (OWIS) models address…

In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect labels is…

The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to…

In this paper, we present and study a new image segmentation task, called Generalized Open-set Semantic Segmentation (GOSS). Previously, with the well-known open-set semantic segmentation (OSS), the intelligent agent only detects the…

Deep metric learning aims to learn a function mapping image pixels to embedding feature vectors that model the similarity between images. Two major applications of metric learning are content-based image retrieval and face verification. For…

Open set recognition (OSR) and continual learning are two critical challenges in machine learning, focusing respectively on detecting novel classes at inference time and updating models to incorporate the new classes. While many recent…

In semi-supervised semantic segmentation, existing studies have shown promising results in academic settings with controlled splits of benchmark datasets. However, the potential benefits of leveraging significantly larger sets of unlabeled…

Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high…

Fine-grained open-set recognition (FineOSR) aims to recognize images belonging to classes with subtle appearance differences while rejecting images of unknown classes. A recent trend in OSR shows the benefit of generative models to…

Code embeddings capture the semantic representations of code and are crucial for various code-related large language model (LLM) applications, such as code search. Previous training primarily relies on optimizing the InfoNCE loss by…

Weakly supervised text classification methods typically train a deep neural classifier based on pseudo-labels. The quality of pseudo-labels is crucial to final performance but they are inevitably noisy due to their heuristic nature, so…