Related papers: From Open Vocabulary to Open World: Teaching Visio…

Traditional LiDAR-based object detection research primarily focuses on closed-set scenarios, which falls short in complex real-world applications. Directly transferring existing 2D open-vocabulary models with some known LiDAR classes for…

Open-vocabulary object detection aims to detect arbitrary classes via text prompts. Methods without cross-modal fusion layers (non-fusion) offer faster inference by treating recognition as a retrieval problem, \ie, matching regions to text…

This paper addresses the significant challenge in open-set object detection (OSOD): the tendency of state-of-the-art detectors to erroneously classify unknown objects as known categories with high confidence. We present a novel approach…

Learning from pseudo-labels that generated with VLMs~(Vision Language Models) has been shown as a promising solution to assist open vocabulary detection (OVD) in recent studies. However, due to the domain gap between VLM and…

As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (a) they have learned before and (b) detect items that they have never seen or learned, and (2) learn…

The challenge of Out-Of-Distribution (OOD) robustness remains a critical hurdle towards deploying deep vision models. Vision-Language Models (VLMs) have recently achieved groundbreaking results. VLM-based open-vocabulary object detection…

Fine-grained open-vocabulary object detection (FG-OVD) aims to detect novel object categories described by attribute-rich texts. While existing open-vocabulary detectors show promise at the base-category level, they underperform in…

Object detection (OD) is crucial to autonomous driving. On the other hand, unknown objects, which have not been seen in training sample set, are one of the reasons that hinder autonomous vehicles from driving beyond the operational domain.…

The growing demand for oriented object detection (OOD) across various domains has driven significant research in this area. However, the high cost of dataset annotation remains a major concern. Current mainstream OOD algorithms can be…

In this paper, we consider the problem of simultaneously detecting objects and inferring their visual attributes in an image, even for those with no manual annotations provided at the training stage, resembling an open-vocabulary scenario.…

Current Zero-Shot Learning (ZSL) approaches are restricted to recognition of a single dominant unseen object category in a test image. We hypothesize that this setting is ill-suited for real-world applications where unseen objects appear…

Weakly Supervised Object Detection (WSOD) is a task that detects objects in an image using a model trained only on image-level annotations. Current state-of-the-art models benefit from self-supervised instance-level supervision, but since…

The You Only Look Once (YOLO) series of detectors have established themselves as efficient and practical tools. However, their reliance on predefined and trained object categories limits their applicability in open scenarios. Addressing…

Object navigation (ObjectNav) requires an agent to navigate through unseen environments to find queried objects. Many previous methods attempted to solve this task by relying on supervised or reinforcement learning, where they are trained…

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…

Marine object detection has gained prominence in marine research, driven by the pressing need to unravel oceanic mysteries and enhance our understanding of invaluable marine ecosystems. There is a profound requirement to efficiently and…

Recently, vision-language pre-training shows great potential in open-vocabulary object detection, where detectors trained on base classes are devised for detecting new classes. The class text embedding is firstly generated by feeding…

Semi-Supervised Object Detection (SSOD), aiming to explore unlabeled data for boosting object detectors, has become an active task in recent years. However, existing SSOD approaches mainly focus on horizontal objects, leaving multi-oriented…

Localizing and recognizing objects in the open-ended physical world poses a long-standing challenge within the domain of machine perception. Recent methods have endeavored to address the issue by employing a class-agnostic mask (or box)…

Many open-world applications require the detection of novel objects, yet state-of-the-art object detection and instance segmentation networks do not excel at this task. The key issue lies in their assumption that regions without any…