Related papers: DEIM: DETR with Improved Matching for Fast Converg…

Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their…

Deep Learning (DL) has achieved unprecedented success in various application domains. Meanwhile, model pruning has emerged as a viable solution to reduce the footprint of DL models in mobile applications, without compromising their…

In the paradigm of object detection, the decision head is an important part, which affects detection performance significantly. Yet how to design a high-performance decision head remains to be an open issue. In this paper, we propose a…

Dense Retrieval (DR) is now considered as a promising tool to enhance the memorization capacity of Large Language Models (LLM) such as GPT3 and GPT-4 by incorporating external memories. However, due to the paradigm discrepancy between text…

Data is the cornerstone of deep learning. This paper reveals that the recently developed Diffusion Model is a scalable data engine for object detection. Existing methods for scaling up detection-oriented data often require manual collection…

Keypoint detection is the foundation of many computer vision tasks, including image registration, structure-from-motion, 3D reconstruction, visual odometry, and SLAM. Traditional detectors (SIFT, ORB, BRISK, FAST, etc.) and learning-based…

Feature matching is a challenging computer vision task that involves finding correspondences between two images of a 3D scene. In this paper we consider the dense approach instead of the more common sparse paradigm, thus striving to find…

Unmanned aerial vehicle object detection (UAV-OD) has been widely used in various scenarios. However, most existing UAV-OD algorithms rely on manually designed components, which require extensive tuning. End-to-end models that do not depend…

This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…

Recent advances in geometric foundation models have emerged as a promising alternative for addressing the challenge of dense reconstruction in monocular visual simultaneous localization and mapping (SLAM). Although geometric foundation…

To accommodate rapid changes in the real world, the cognition system of humans is capable of continually learning concepts. On the contrary, conventional deep learning models lack this capability of preserving previously learned knowledge.…

Recently, DETR pioneered the solution of vision tasks with transformers, it directly translates the image feature map into the object detection result. Though effective, translating the full feature map can be costly due to redundant…

This paper investigates the problem of object detection with a focus on improving both the localization accuracy of bounding boxes and explicitly modeling prediction uncertainty. Conventional detectors rely on deterministic bounding box…

Since the development of self-supervised visual representation learning from contrastive learning to masked image modeling (MIM), there is no significant difference in essence, that is, how to design proper pretext tasks for vision…

This article presents GLIM, a 3D range-inertial localization and mapping framework with GPU-accelerated scan matching factors. The odometry estimation module of GLIM employs a combination of fixed-lag smoothing and keyframe-based point…

Recent camera-based 3D object detection is limited by the precision of transforming from image to 3D feature spaces, as well as the accuracy of object localization within the 3D space. This paper aims to address such a fundamental problem…

Computationally efficient moving object detection and depth estimation from a stereo camera is an extremely useful tool for many computer vision applications, including robotics and autonomous driving. In this paper we show how moving…

Simultaneously optimizing multiple, frequently conflicting, molecular properties is a key bottleneck in the development of novel therapeutics. Although a promising approach, the efficacy of multi-task learning is often compromised by…

Learning large scale nonlinear ordinary differential equation (ODE) systems from data is known to be computationally and statistically challenging. We present a framework together with the adaptive integral matching (AIM) algorithm for…

Object detection has made tremendous strides in computer vision. Small object detection with appearance degradation is a prominent challenge, especially for aerial observations. To collect sufficient positive/negative samples for heuristic…