Related papers: Align-DETR: Enhancing End-to-end Object Detection …

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…

Mixture models are well-established learning approaches that, in computer vision, have mostly been applied to inverse or ill-defined problems. However, they are general-purpose divide-and-conquer techniques, splitting the input space into…

Convolutional neural networks (CNNs) based approaches for semantic alignment and object landmark detection have improved their performance significantly. Current efforts for the two tasks focus on addressing the lack of massive training…

In the field of deep learning based computer vision, the development of deep object detection has led to unique paradigms (e.g., two-stage or set-based) and architectures (e.g., Faster-RCNN or DETR) which enable outstanding performance on…

We present DINO (\textbf{D}ETR with \textbf{I}mproved de\textbf{N}oising anch\textbf{O}r boxes), a state-of-the-art end-to-end object detector. % in this paper. DINO improves over previous DETR-like models in performance and efficiency by…

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…

Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific…

Clothing segmentation and fine-grained attribute recognition are challenging tasks at the crossing of computer vision and fashion, which segment the entire ensemble clothing instances as well as recognize detailed attributes of the clothing…

In this paper, we introduce a novel unbiased regression loss for DETR-based detectors. The conventional $L_{1}$ regression loss tends to bias towards larger boxes, as they disproportionately contribute more towards the overall loss compared…

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…

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…

Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on incremental object…

Dense retrieval systems increasingly need to handle complex queries. In many realistic settings, users express intent through long instructions or task-specific descriptions, while target documents remain relatively simple and static. This…

As a data-driven method, the performance of deep convolutional neural networks (CNN) relies heavily on training data. The prediction results of traditional networks give a bias toward larger classes, which tend to be the background in the…

Common object detection models consist of classification and regression branches, due to different task drivers, these two branches have different sensibility to the features from the same scale level and the same spatial location. The…

This paper introduces the point-axis representation for oriented object detection, emphasizing its flexibility and geometrically intuitive nature with two key components: points and axes. 1) Points delineate the spatial extent and contours…

The modern image search system requires semantic understanding of image, and a key yet under-addressed problem is to learn a good metric for measuring the similarity between images. While deep metric learning has yielded impressive…

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…

Modern pre-trained architectures struggle to retain previous information while undergoing continuous fine-tuning on new tasks. Despite notable progress in continual classification, systems designed for complex vision tasks such as detection…

One-to-one matching is a crucial design in DETR-like object detection frameworks. It enables the DETR to perform end-to-end detection. However, it also faces challenges of lacking positive sample supervision and slow convergence speed.…