Related papers: Semantic Novelty Detection via Relational Reasonin…
Open Set Recognition (OSR) is about dealing with unknown situations that were not learned by the models during training. In this paper, we provide a survey of existing works about OSR and distinguish their respective advantages and…
In this paper, we focus on Novel Class Discovery for Point Cloud Segmentation (3D-NCD), aiming to learn a model that can segment unlabeled (novel) 3D classes using only the supervision from labeled (base) 3D classes. The key to this task is…
We tackle the novel class discovery in point cloud segmentation, which discovers novel classes based on the semantic knowledge of seen classes. Existing work proposes an online point-wise clustering method with a simplified equal class-size…
Relationships among objects play a crucial role in image understanding. Despite the great success of deep learning techniques in recognizing individual objects, reasoning about the relationships among objects remains a challenging task.…
In this paper we present a novel method for a naive agent to detect novel objects it encounters in an interaction. We train a reinforcement learning policy on a stacking task given a known object type, and then observe the results of the…
Sentence semantic matching is one of the fundamental tasks in natural language processing, which requires an agent to determine the semantic relation among input sentences. Recently, deep neural networks have achieved impressive performance…
Image-based environment perception is an important component especially for driver assistance systems or autonomous driving. In this scope, modern neuronal networks are used to identify multiple objects as well as the according position and…
With the human pursuit of knowledge, open-set object detection (OSOD) has been designed to identify unknown objects in a dynamic world. However, an issue with the current setting is that all the predicted unknown objects share the same…
Anomaly detection seeks to identify unusual phenomena, a central task in science and industry. The task is inherently unsupervised as anomalies are unexpected and unknown during training. Recent advances in self-supervised representation…
Generalized Zero-Shot Learning (GZSL) and Open-Set Recognition (OSR) are two mainstream settings that greatly extend conventional visual object recognition. However, the limitations of their problem settings are not negligible. The novel…
Label noise and ambiguities between similar classes are challenging problems in developing new models and annotating new data for semantic segmentation. In this paper, we propose Compensation Learning in Semantic Segmentation, a framework…
Visual concept discovery has long been deemed important to improve interpretability of neural networks, because a bank of semantically meaningful concepts would provide us with a starting point for building machine learning models that…
After being trained on a fully-labeled training set, where the observations are grouped into a certain number of known classes, novelty detection methods aim to classify the instances of an unlabeled test set while allowing for the presence…
Novelty detection is a task of machine learning that aims at detecting novel events without a prior knowledge. In particular, its techniques can be applied to detect unexpected signals from new phenomena at colliders. In this paper, we…
The ability to identify whether or not a test sample belongs to one of the semantic classes in a classifier's training set is critical to practical deployment of the model. This task is termed open-set recognition (OSR) and has received…
For the semantic segmentation of images, state-of-the-art deep neural networks (DNNs) achieve high segmentation accuracy if that task is restricted to a closed set of classes. However, as of now DNNs have limited ability to operate in an…
Novel Class Discovery (NCD) aims at inferring novel classes in an unlabeled set by leveraging prior knowledge from a labeled set with known classes. Despite its importance, there is a lack of theoretical foundations for NCD. This paper…
Motivated by the increasing popularity of transformers in computer vision, in recent times there has been a rapid development of novel architectures. While in-domain performance follows a constant, upward trend, properties like robustness…
Open set domain recognition has got the attention in recent years. The task aims to specifically classify each sample in the practical unlabeled target domain, which consists of all known classes in the manually labeled source domain and…
We consider the problem of discovering novel object categories in an image collection. While these images are unlabelled, we also assume prior knowledge of related but different image classes. We use such prior knowledge to reduce the…