Related papers: DN-DETR: Accelerate DETR Training by Introducing Q…

Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output high-quality…

Recently, two-stage Deformable DETR introduced the query-based two-stage head, a new type of two-stage head different from the region-based two-stage heads of classical detectors as Faster R-CNN. In query-based two-stage heads, the second…

Nuclear Magnetic Resonance (NMR) spectroscopy is a widely-used technique in the fields of bio-medicine, chemistry, and biology for the analysis of chemicals and proteins. The signals from NMR spectroscopy often have low signal-to-noise…

While DETR-like architectures have demonstrated significant potential for monocular 3D object detection, they are often hindered by a critical limitation: the exclusion of 3D attributes from the bipartite matching process. This exclusion…

Model-based optimization methods and discriminative learning methods have been the two dominant strategies for solving various inverse problems in low-level vision. Typically, those two kinds of methods have their respective merits and…

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…

Visual anomaly detection, an important problem in computer vision, is usually formulated as a one-class classification and segmentation task. The student-teacher (S-T) framework has proved to be effective in solving this challenge. However,…

A fundamental challenge in imitation learning is the \emph{covariate shift} problem. Existing methods to mitigate covariate shift often require additional expert interactions, access to environment dynamics, or complex adversarial training,…

Detection Transformer (DETR) is a Transformer architecture based object detection model. In this paper, we demonstrate that it can also be used as a data augmenter. We term our approach as DETR assisted CutMix, or DeMix for short. DeMix…

In medical image segmentation, domain generalization poses a significant challenge due to domain shifts caused by variations in data acquisition devices and other factors. These shifts are particularly pronounced in the most common…

Recently, the dominant DETR-based approaches apply central-concept spatial prior to accelerate Transformer detector convergency. These methods gradually refine the reference points to the center of target objects and imbue object queries…

Traditional denoising methods for noise removal have largely relied on handcrafted priors, often perform well in controlled environments but struggle to address the complexity and variability of real noise. In contrast, deep learning-based…

Underwater object detection has higher requirements of running speed and deployment efficiency for the detector due to its specific environmental challenges. NMS of two- or one-stage object detectors and transformer architecture of…

In dense retrieval, deep encoders provide embeddings for both inputs and targets, and the softmax function is used to parameterize a distribution over a large number of candidate targets (e.g., textual passages for information retrieval).…

Atrous convolutions are employed as a method to increase the receptive field in semantic segmentation tasks. However, in previous works of semantic segmentation, it was rarely employed in the shallow layers of the model. We revisit the…

Regularization by denoising (RED) is a recently developed framework for solving inverse problems by integrating advanced denoisers as image priors. Recent work has shown its state-of-the-art performance when combined with pre-trained deep…

The large volumes of Sentinel-1 data produced over Europe are being used to develop pan-national ground motion services. However, simple analysis techniques like thresholding cannot detect and classify complex deformation signals reliably…

Compared to monocular 3D object detection, stereo-based 3D methods offer significantly higher accuracy but still suffer from high computational overhead and latency. The state-of-the-art stereo 3D detection method achieves twice the…

Measuring domain relevance of data and identifying or selecting well-fit domain data for machine translation (MT) is a well-studied topic, but denoising is not yet. Denoising is concerned with a different type of data quality and tries to…

In PET, the amount of relative (signal-dependent) noise present in different body regions can be significantly different and is inherently related to the number of counts present in that region. The number of counts in a region depends, in…