MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations

2025-03-18 · Hongyu Ke, Jack Morris, Kentaro Oguchi, Xiaofei Cao, Yongkang Liu, Haoxin Wang, Yi Ding

3D visual perception tasks, such as 3D detection from multi-camera images, are essential components of autonomous driving and assistance systems. However, designing computationally efficient methods remains a significant challenge. In this paper, we propose a Mamba-based framework called MamBEV, which learns unified Bird's Eye View (BEV) representations using linear spatio-temporal SSM-based attention. This approach supports multiple 3D perception tasks with significantly improved computational and memory efficiency. Furthermore, we introduce SSM based cross-attention, analogous to standard cross attention, where BEV query representations can interact with relevant image features. Extensive experiments demonstrate MamBEV's promising performance across diverse visual perception metrics, highlighting its advantages in input scaling efficiency compared to existing benchmark models.

📄 PDF Abstract BibTeX arXiv:2503.13858

Code (1)

amai-gsu/mambev 공식 구현 pytorch

Tasks

Autonomous DrivingMambaState Space Models

Deep Q-Network for Angry Birds

2019-10-04 · Ekaterina Nikonova, Jakub Gemrot

Angry Birds is a popular video game in which the player is provided with a sequence of birds to shoot from a slingshot. The task of the game is to destroy all green pigs with maximum possible score. Angry Birds appears t…

Decision Making Deep Reinforcement Learning Reinforcement Learning Sequential Decision Making

Birds of a Feather: Capturing Avian Shape Models from Images

2021-05-19 · CVPR 2021 1 · Yufu Wang, Nikos Kolotouros, Kostas Daniilidis, Marc Badger

Animals are diverse in shape, but building a deformable shape model for a new species is not always possible due to the lack of 3D data. We present a method to capture new species using an articulated template and images…

Angrier Birds: Bayesian reinforcement learning

2016-01-06 · Imanol Arrieta Ibarra, Bernardo Ramos, Lars Roemheld

We train a reinforcement learner to play a simplified version of the game Angry Birds. The learner is provided with a game state in a manner similar to the output that could be produced by computer vision algorithms. We …

Efficient Exploration Q-Learning reinforcement-learning Reinforcement Learning+1

BirdSAT: Cross-View Contrastive Masked Autoencoders for Bird Species Classification and Mapping

2023-10-29 · Srikumar Sastry, Subash Khanal, Aayush Dhakal, Di Huang 외

We propose a metadata-aware self-supervised learning~(SSL)~framework useful for fine-grained classification and ecological mapping of bird species around the world. Our framework unifies two SSL strategies: Contrastive L…

Contrastive Learning Cross-Modal Retrieval Fine-Grained Image Classification Retrieval+2

Aphids, Ants and Ladybirds: a mathematical model predicting their population dynamics

2019-05-13

The interaction between aphids, ants and ladybirds has been investigated from an ecological point of view since many decades, while there are no attempts to describe it from a mathematical point of view. This paper intro…

Time Series Analysis