Related papers: Recognizing Unseen States of Unknown Objects by Le…

As we move towards large-scale object detection, it is unrealistic to expect annotated training data, in the form of bounding box annotations around objects, for all object classes at sufficient scale, and so methods capable of unseen…

Acquiring knowledge about object interactions and affordances can facilitate scene understanding and human-robot collaboration tasks. As humans tend to use objects in many different ways depending on the scene and the objects' availability,…

In a real-world setting, visual recognition systems can be brought to make predictions for images belonging to previously unknown class labels. In order to make semantically meaningful predictions for such inputs, we propose a two-step…

Object-centric learning (OCL) seeks to learn representations that only encode an object, isolated from other objects or background cues in a scene. This approach underpins various aims, including out-of-distribution (OOD) generalization,…

This work introduces a model that can recognize objects in images even if no training data is available for the objects. The only necessary knowledge about the unseen categories comes from unsupervised large text corpora. In our zero-shot…

Visual object counting has recently shifted towards class-agnostic counting (CAC), which addresses the challenge of counting objects across arbitrary categories, a crucial capability for flexible and generalizable counting systems. Unlike…

We propose a new approach for Zero-Shot Human-Object Interaction Recognition in the challenging setting that involves interactions with unseen actions (as opposed to just unseen combinations of seen actions and objects). Our approach makes…

Recent object detectors have achieved impressive accuracy in identifying objects seen during training. However, real-world deployment often introduces novel and unexpected objects, referred to as out-of-distribution (OOD) objects, posing…

Open-set object detection (OSOD) aims to detect the known categories and reject unknown objects in a dynamic world, which has achieved significant attention. However, previous approaches only consider this problem in data-abundant…

Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and annotating detection datasets, trained models detect a…

This paper investigates the problem of zero-shot action recognition, in the setting where no training videos with seen actions are available. For this challenging scenario, the current leading approach is to transfer knowledge from the…

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…

This paper addresses the semantic instance segmentation task in the open-set conditions, where input images can contain known and unknown object classes. The training process of existing semantic instance segmentation methods requires…

Open World Object Detection (OWOD) is a challenging computer vision problem that requires detecting unknown objects and gradually learning the identified unknown classes. However, it cannot distinguish unknown instances as multiple unknown…

Traditional image recognition methods only consider objects belonging to already learned classes. However, since training a recognition model with every object class in the world is unfeasible, a way of getting information on unknown…

Open-Set Object Detection (OSOD) is crucial for autonomous driving, where perception systems must recognize and localize both known and previously unseen objects in complex, dynamic environments. While recent approaches deliver promising…

Class-agnostic object counting aims to count object instances of an arbitrary class at test time. It is challenging but also enables many potential applications. Current methods require human-annotated exemplars as inputs which are often…

Open-set object detection (OSOD), a task involving the detection of unknown objects while accurately detecting known objects, has recently gained attention. However, we identify a fundamental issue with the problem formulation employed in…

Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which…

Recent works on predictive uncertainty estimation have shown promising results on Out-Of-Distribution (OOD) detection for semantic segmentation. However, these methods struggle to precisely locate the point of interest in the image, i.e,…