paper-with-me

홈 › Papers

Percept, Memory, and Imagine: World Feature Simulating for Open-Domain Unknown Object Detection

2025-01-01 · CVPR 2025 1 · Aming Wu, Cheng Deng

To accelerate the safe deployment of object detectors, we focus on reducing the impact of both covariate and semantic shifts. And we consider a realistic yet challenging scenario, namely Open-Domain Unknown Object Detection (ODU-OD), which aims to detect unknown objects in unseen target domains without accessing any auxiliary data. Towards ODU-OD, it is feasible to learn a robust discriminative boundary by synthesizing virtual features. Generally, perception, memory, and imagination are three essential capacities for human beings. Through multi-level perception and rich memory about known objects, the characteristics of unknown objects can be imagined sufficiently, enhancing the ability of discriminating known from unknown objects. Inspired by this idea, an approach of World Feature Simulation (WFS) is proposed, mainly consisting of a multi-level perception, memory recorder, and unknown-feature generator. Specifically, after extracting the features of the input, we separately employ a Mamba and Graph Network to obtain the global-level and connective-level representations. Next, a codebook containing multiple learnable codewords is defined to preserve fragmented memory of known objects. Meanwhile, we perform a modulated operation on the memory to form the imagination bank involving unknown characteristics. Finally, to alleviate the impact of lacking supervision data, based on the multi-level representation and imagination bank, a dedicated unknown-feature generator is designed to recurrently synthesize outlier features deviating from in-distribution (ID) objects. The significant performance gains on four different detection tasks demonstrate the superiorities of our method. The code will be released at https://github.com/AmingWu/WFS.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Mambaobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Mamba Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.…

Similar Papers 제목 키워드 기반

On Memory: A comparison of memory mechanisms in world models

2025-12-07 · Eli J. Laird, Corey Clark arxiv

World models enable agents to plan within imagined environments by predicting future states conditioned on past observations and actions. However, their ability to plan over long horizons is limited by the effective memo…

MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models

2026-06-08 · Hao Shi, Weiye Li, Bin Xie, Yulin Wang 외 arxiv

Temporal modeling is essential for robotic manipulation, as effective control requires both memory of past interactions and imagination of future states. However, most VLA models rely primarily on the current observation…

Towards Unified World Models for Visual Navigation via Memory-Augmented Planning and Foresight

2025-10-09 · Yifei Dong, Fengyi Wu, Guangyu Chen, Lingdong Kong 외 arxiv

Enabling embodied agents to imagine future states is essential for robust and generalizable visual navigation. Yet, state-of-the-art systems typically rely on modular designs that decouple navigation planning from visual…

Visual Navigation

Scaling Face Interaction Graph Networks to Real World Scenes

2024-01-22 · Tatiana Lopez-Guevara, Yulia Rubanova, William F. Whitney, Tobias Pfaff 외

Accurately simulating real world object dynamics is essential for various applications such as robotics, engineering, graphics, and design. To better capture complex real dynamics such as contact and friction, learned si…

Friction

ImagineNav++: Prompting Vision-Language Models as Embodied Navigator through Scene Imagination

2025-12-19 · Teng Wang, Xinxin Zhao, Wenzhe Cai, Changyin Sun arxiv

Visual navigation is a fundamental capability for autonomous home-assistance robots, enabling long-horizon tasks such as object search. While recent methods have leveraged Large Language Models (LLMs) to incorporate comm…

Spatial ReasoningVisual Navigation