Related papers: SO-DETR: Leveraging Dual-Domain Features and Knowl…
DETR is a novel end-to-end transformer architecture object detector, which significantly outperforms classic detectors when scaling up. In this paper, we focus on the compression of DETR with knowledge distillation. While knowledge…
The main challenge for small object detection algorithms is to ensure accuracy while pursuing real-time performance. The RT-DETR model performs well in real-time object detection, but performs poorly in small object detection accuracy. In…
Transformers have revolutionized the object detection landscape by introducing DETRs, acclaimed for their simplicity and efficacy. Despite their advantages, the substantial size of these models poses significant challenges for practical…
Detecting tiny objects plays a vital role in remote sensing intelligent interpretation, as these objects often carry critical information for downstream applications. However, due to the extremely limited pixel information and significant…
Transformer-based detectors (DETRs) are becoming popular for their simple framework, but the large model size and heavy time consumption hinder their deployment in the real world. While knowledge distillation (KD) can be an appealing…
Small Object Detection (SOD) poses significant challenges due to limited information and the model's low class prediction score. While Transformer-based detectors have shown promising performance, their potential for SOD remains largely…
The recent detection transformer (DETR) has advanced object detection, but its application on resource-constrained devices requires massive computation and memory resources. Quantization stands out as a solution by representing the network…
The recent detection transformer (DETR) simplifies the object detection pipeline by removing hand-crafted designs and hyperparameters as employed in conventional two-stage object detectors. However, how to leverage the simple yet effective…
In this paper, we address the limitations of the DETR-based semi-supervised object detection (SSOD) framework, particularly focusing on the challenges posed by the quality of object queries. In DETR-based SSOD, the one-to-one assignment…
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…
Tiny object detection is one of the key challenges in the field of object detection. The performance of most generic detectors dramatically decreases in tiny object detection tasks. The main challenge lies in extracting effective features…
Incremental object detection (IOD) aims to train an object detector in phases, each with annotations for new object categories. As other incremental settings, IOD is subject to catastrophic forgetting, which is often addressed by techniques…
Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…
We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo ground-truth bounding box is inaccurate, leading to training…
Popular transformer detectors have achieved promising performance through query-based learning using attention mechanisms. However, the roles of existing decoder query types (e.g., content query and positional query) are still…
Transformers have rapidly gained popularity in computer vision, especially in the field of object recognition and detection. Upon examining the outcomes of state-of-the-art object detection methods, we noticed that transformers consistently…
Infrared small object detection urgently requires semi-supervised paradigms due to the high cost of annotation. However, existing methods like SAM face significant challenges of domain gaps, inability of encoding physical priors, and…
Object detection via inaccurate bounding boxes supervision has boosted a broad interest due to the expensive high-quality annotation data or the occasional inevitability of low annotation quality (\eg tiny objects). The previous works…
Small object detection (SOD) is a critical yet challenging task in computer vision, with applications like spanning surveillance, autonomous systems, medical imaging, and remote sensing. Unlike larger objects, small objects contain limited…
Despite previous DETR-like methods having performed successfully in generic object detection, tiny object detection is still a challenging task for them since the positional information of object queries is not customized for detecting tiny…