paper-with-me

Papers

MAD: Memory-Augmented Detection of 3D Objects

2025-01-01 · CVPR 2025 1 · Ben Agro, Sergio Casas, Patrick Wang, Thomas Gilles, Raquel Urtasun

To perceive, humans use memory to fill in gaps caused by our limited visibility, whether due to occlusion or our narrow field of view. However, most 3D object detectors are limited to using sensor evidence from a short temporal window (0.1s-0.3s). In this work, we present a simple and effective add-on for enhancing any existing 3D object detector with long-term memory regardless of its sensor modality (e.g., LiDAR, camera) and network architecture. We propose a model to effectively align and fuse object proposals from a detector with object proposals from a memory bank of past predictions, exploiting trajectory forecasts to align proposals across time. We propose a novel schedule to train our model on temporal data that balances data diversity and the gap between training and inference. By applying our method to existing LiDAR and camera-based detectors on the Waymo Open Dataset (WOD) and Argoverse 2 Sensor (AV2) dataset, we demonstrate significant improvements in detection performance (+2.5 to +7.6 AP points). Our method attains the best performance on the WOD 3D detection leaderboard among online methods (excluding ensembles or test-time augmentation).

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Object

Methods 이 논문이 사용한 방법론

ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

ODDObjects: A Framework for Multiclass Unsupervised Anomaly Detection on Masked Objects

2021-04-26 · Ricky Ma

This paper presents a novel framework for unsupervised anomaly detection on masked objects called ODDObjects, which stands for Out-of-Distribution Detection on Objects. ODDObjects is designed to detect anomalies of vario…

Anomaly DetectionImage ReconstructionObject RecognitionOut-of-Distribution Detection+1

Prompt-responsive Object Retrieval with Memory-augmented Student-Teacher Learning

2025-05-04 · Malte Mosbach, Sven Behnke

Building models responsive to input prompts represents a transformative shift in machine learning. This paradigm holds significant potential for robotics problems, such as targeted manipulation amidst clutter. In this wo…

Reinforcement Learning (RL)RetrievalState Estimation

Memory Augmented Generative Adversarial Networks for Anomaly Detection

2020-02-07 · Ziyi Yang, Teng Zhang, Iman Soltani Bozchalooi, Eric Darve

In this paper, we present a memory-augmented algorithm for anomaly detection. Classical anomaly detection algorithms focus on learning to model and generate normal data, but typically guarantees for detecting anomalous d…

Anomaly Detection

EVCap: Retrieval-Augmented Image Captioning with External Visual-Name Memory for Open-World Comprehension

2023-11-27 · CVPR 2024 1 · Jiaxuan Li, Duc Minh Vo, Akihiro Sugimoto, Hideki Nakayama

Large language models (LLMs)-based image captioning has the capability of describing objects not explicitly observed in training data; yet novel objects occur frequently, necessitating the requirement of sustaining up-to…

Image CaptioningObjectRetrieval

Clear Memory-Augmented Auto-Encoder for Surface Defect Detection

2022-08-08 · Wei Luo, Tongzhi Niu, Lixin Tang, Wenyong Yu 외

In surface defect detection, due to the extreme imbalance in the number of positive and negative samples, positive-samples-based anomaly detection methods have received more and more attention. Specifically, reconstructi…

Anomaly DetectionDefect Detection