Related papers: Lite DETR : An Interleaved Multi-Scale Encoder for…

The Detection Transformer (DETR), by incorporating the Hungarian algorithm, has significantly simplified the matching process in object detection tasks. This algorithm facilitates optimal one-to-one matching of predicted bounding boxes to…

Query-based methods have garnered significant attention in object detection since the advent of DETR, the pioneering query-based detector. However, these methods face challenges like slow convergence and suboptimal performance. Notably,…

The introduction of DETR represents a new paradigm for object detection. However, its decoder conducts classification and box localization using shared queries and cross-attention layers, leading to suboptimal results. We observe that…

Multi-camera tracking plays a pivotal role in various real-world applications. While end-to-end methods have gained significant interest in single-camera tracking, multi-camera tracking remains predominantly reliant on heuristic techniques.…

Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works…

Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…

The Detection Transformer (DETR) has revolutionized the design of CNN-based object detection systems, showcasing impressive performance. However, its potential in the domain of multi-frame 3D object detection remains largely unexplored. In…

The training paradigm of DETRs is heavily contingent upon pre-training their backbone on the ImageNet dataset. However, the limited supervisory signals provided by the image classification task and one-to-one matching strategy result in an…

Multi-scale features have been proven highly effective for object detection but often come with huge and even prohibitive extra computation costs, especially for the recent Transformer-based detectors. In this paper, we propose Iterative…

Few-shot object detection has been extensively investigated by incorporating meta-learning into region-based detection frameworks. Despite its success, the said paradigm is constrained by several factors, such as (i) low-quality region…

Small object detection remains a significant challenge due to feature degradation from downsampling, mutual occlusion in dense clusters, and complex background interference. To address these issues, this paper proposes FSDETR, a…

Multimodal remote sensing object detection aims to achieve more accurate and robust perception under challenging conditions by fusing complementary information from different modalities. However, existing approaches that rely on…

DETR accomplishes end-to-end object detection through iteratively generating multiple object candidates based on image features and promoting one candidate for each ground-truth object. The traditional training procedure using one-to-one…

Recently, 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 performance on…

This paper is concerned with the matching stability problem across different decoder layers in DEtection TRansformers (DETR). We point out that the unstable matching in DETR is caused by a multi-optimization path problem, which is…

The DETR object detection approach applies the transformer encoder and decoder architecture to detect objects and achieves promising performance. In this paper, we present a simple approach to address the main problem of DETR, the slow…

Standard inference and training with transformer based architectures scale quadratically with input sequence length. This is prohibitively large for a variety of applications especially in web-page translation, query-answering etc.…

Detection Transformer (DETR) directly transforms queries to unique objects by using one-to-one bipartite matching during training and enables end-to-end object detection. Recently, these models have surpassed traditional detectors on COCO…

The ability to detect objects in images at varying scales has played a pivotal role in the design of modern object detectors. Despite considerable progress in removing hand-crafted components and simplifying the architecture with…

Detection Transformer (DETR) has redefined object detection by casting it as a set prediction task within an end-to-end framework. Despite its elegance, DETR and its variants still rely on fixed learnable queries and suffer from severe…