Related papers: DETRs with Hybrid Matching
Ultra-High-Resolution (UHR) imagery has become essential for modern remote sensing, offering unprecedented spatial coverage. However, detecting small objects in such vast scenes presents a critical dilemma: retaining the original resolution…
Drone detection is pivotal in numerous security and counter-UAV applications. However, existing deep learning-based methods typically struggle to balance robust feature representation with computational efficiency. This challenge is…
Hyperspectral target detection (HTD) aims to identify specific materials based on spectral information in hyperspectral imagery and can detect extremely small-sized objects, some of which occupy a smaller than one-pixel area. However,…
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…
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…
Existing approaches for video moment retrieval and highlight detection are not able to align text and video features efficiently, resulting in unsatisfying performance and limited production usage. To address this, we propose a novel…
DETR-like models have significantly boosted the performance of detectors and even outperformed classical convolutional models. However, all tokens are treated equally without discrimination brings a redundant computational burden in the…
Detection Transformers (DETR) have recently set new benchmarks in object detection. However, their performance in detecting rotated objects lags behind established oriented object detectors. Our analysis identifies a key observation: the…
DEtection TRansformer (DETR) becomes a dominant paradigm, mainly due to its common architecture with high accuracy and no post-processing. However, DETR suffers from unstable training dynamics. It consumes more data and epochs to converge…
Self-supervised pre-training and transformer-based networks have significantly improved the performance of object detection. However, most of the current self-supervised object detection methods are built on convolutional-based…
Recently, object detection models have witnessed notable performance improvements, particularly with transformer-based models. However, new objects frequently appear in the real world, requiring detection models to continually learn without…
Arbitrary-oriented object detection (AOOD) is a challenging task to detect objects in the wild with arbitrary orientations and cluttered arrangements. Existing approaches are mainly based on anchor-based boxes or dense points, which rely on…
We propose 3DETR, an end-to-end Transformer based object detection model for 3D point clouds. Compared to existing detection methods that employ a number of 3D-specific inductive biases, 3DETR requires minimal modifications to the vanilla…
Object detection in Unmanned Aerial Vehicle (UAV) imagery is fundamentally challenged by a prevalence of small, densely packed, and occluded objects within cluttered backgrounds. Conventional detectors struggle with this domain, as they…
Financial institutions and businesses face an ongoing challenge from fraudulent transactions, prompting the need for effective detection methods. Detecting credit card fraud is crucial for identifying and preventing unauthorized…
We present a novel method for efficiently producing semi-dense matches across images. Previous detector-free matcher LoFTR has shown remarkable matching capability in handling large-viewpoint change and texture-poor scenarios but suffers…
Vision transformers (ViTs) are changing the landscape of object detection approaches. A natural usage of ViTs in detection is to replace the CNN-based backbone with a transformer-based backbone, which is straightforward and effective, with…
Depth from defocus (DfD) and stereo matching are two most studied passive depth sensing schemes. The techniques are essentially complementary: DfD can robustly handle repetitive textures that are problematic for stereo matching whereas…
Indoor radar perception has seen rising interest due to affordable costs driven by emerging automotive imaging radar developments and the benefits of reduced privacy concerns and reliability under hazardous conditions (e.g., fire and…
Object detection is one of the most significant aspects of computer vision, and it has achieved substantial results in a variety of domains. It is worth noting that there are few studies focusing on slender object detection. CNNs are widely…