Related papers: MS-DETR: Efficient DETR Training with Mixed Superv…
The astounding performance of transformers in natural language processing (NLP) has motivated researchers to explore their applications in computer vision tasks. DEtection TRansformer (DETR) introduces transformers to object detection tasks…
DETR is the first end-to-end object detector using a transformer encoder-decoder architecture and demonstrates competitive performance but low computational efficiency on high resolution feature maps. The subsequent work, Deformable DETR,…
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…
The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN. However, DETR suffers from…
The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Previous works typically add expensive modules to DETR to…
Zero-shot object detection aims to localize and recognize objects of unseen classes. Most of existing works face two problems: the low recall of RPN in unseen classes and the confusion of unseen classes with background. In this paper, we…
Multi-modal reasoning systems rely on a pre-trained object detector to extract regions of interest from the image. However, this crucial module is typically used as a black box, trained independently of the downstream task and on a fixed…
3D object detection is a significant task for autonomous driving. Recently with the progress of vision transformers, the 2D object detection problem is being treated with the set-to-set loss. Inspired by these approaches on 2D object…
Video Moment Retrieval (MR) and Highlight Detection (HD) aim to pinpoint specific moments and assess clip-wise relevance based on the text query. While DETR-based joint frameworks have made significant strides, there remains untapped…
Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method…
Open world object detection aims at detecting objects that are absent in the object classes of the training data as unknown objects without explicit supervision. Furthermore, the exact classes of the unknown objects must be identified…
Self-supervised learning (SSL) methods such as masked language modeling have shown massive performance gains by pretraining transformer models for a variety of natural language processing tasks. The follow-up research adapted similar…
Object detection is an important topic in computer vision, with post-processing, an essential part of the typical object detection pipeline, posing a significant bottleneck affecting the performance of traditional object detection models.…
In this paper, we are interested in Detection Transformer (DETR), an end-to-end object detection approach based on a transformer encoder-decoder architecture without hand-crafted postprocessing, such as NMS. Inspired by Conditional DETR, an…
Motivated by the remarkable achievements of DETR-based approaches on COCO object detection and segmentation benchmarks, recent endeavors have been directed towards elevating their performance through self-supervised pre-training of…
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…
The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN. However, DETR suffers from…
This paper presents a general scheme for enhancing the convergence and performance of DETR (DEtection TRansformer). We investigate the slow convergence problem in transformers from a new perspective, suggesting that it arises from the…
Recent self-supervised methods are mainly designed for representation learning with the base model, e.g., ResNets or ViTs. They cannot be easily transferred to DETR, with task-specific Transformer modules. In this work, we present Siamese…
Unknown Object Detection (UOD) aims to identify objects of unseen categories, differing from the traditional detection paradigm limited by the closed-world assumption. A key component of UOD is learning a generalized representation, i.e.…