Related papers: Decoupled DETR: Spatially Disentangling Localizati…
DETR-like methods have significantly increased detection performance in an end-to-end manner. The mainstream two-stage frameworks of them perform dense self-attention and select a fraction of queries for sparse cross-attention, which is…
This paper takes an important step in bridging the performance gap between DETR and R-CNN for graphical object detection. Existing graphical object detection approaches have enjoyed recent enhancements in CNN-based object detection methods,…
We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object contours. Our network is…
We present a new model named Stacked-DETR(SDETR), which inherits the main ideas in canonical DETR. We improve DETR in two directions: simplifying the cost of training and introducing the stacked architecture to enhance the performance. To…
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.…
To improve the generalization of detectors, for domain adaptive object detection (DAOD), recent advances mainly explore aligning feature-level distributions between the source and single-target domain, which may neglect the impact of…
Image segmentation needs both local boundary position information and global object context information. The performance of the recent state-of-the-art method, fully convolutional networks, reaches a bottleneck due to the neural network…
Moving objects have special importance for Autonomous Driving tasks. Detecting moving objects can be posed as Moving Object Segmentation, by segmenting the object pixels, or Moving Object Detection, by generating a bounding box for the…
Temporal Action Detection (TAD) is challenging but fundamental for real-world video applications. Recently, DETR-based models have been devised for TAD but have not performed well yet. In this paper, we point out the problem in the…
Transformer-based architectures have established a dominant paradigm in global semantic perception; however, they remain fundamentally constrained by the profound spatial heterogeneity inherent in natural images. Specifically, the…
We propose ST-DETR, a Spatio-Temporal Transformer-based architecture for object detection from a sequence of temporal frames. We treat the temporal frames as sequences in both space and time and employ the full attention mechanisms to take…
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…
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…
We propose a new task and model for dense video object captioning -- detecting, tracking and captioning trajectories of objects in a video. This task unifies spatial and temporal localization in video, whilst also requiring fine-grained…
Training high-accuracy 3D detectors necessitates massive labeled 3D annotations with 7 degree-of-freedom, which is laborious and time-consuming. Therefore, the form of point annotations is proposed to offer significant prospects for…
Various models have been proposed to perform object detection. However, most require many handdesigned components such as anchors and non-maximum-suppression(NMS) to demonstrate good performance. To mitigate these issues, Transformer-based…
Accents, as variations from standard pronunciation, pose significant challenges for speech recognition systems. Although joint automatic speech recognition (ASR) and accent recognition (AR) training has been proven effective in handling…
Existing methods enhance the training of detection transformers by incorporating an auxiliary one-to-many assignment. In this work, we treat the model as a multi-task framework, simultaneously performing one-to-one and one-to-many…
Recently, end-to-end object detectors have gained significant attention from the research community due to their outstanding performance. However, DETR typically relies on supervised pretraining of the backbone on ImageNet, which limits the…
We propose MisMatch, a novel consistency-driven semi-supervised segmentation framework which produces predictions that are invariant to learnt feature perturbations. MisMatch consists of an encoder and a two-head decoders. One decoder…