Related papers: Selecting Learnable Training Samples is All DETRs …

Deep learning based object detectors are commonly deployed on mobile devices to solve a variety of tasks. For maximum accuracy, each detector is usually trained to solve one single specific task, and comes with a completely independent set…

Scene Graph Generation (SGG) is a challenging task of detecting objects and predicting relationships between objects. After DETR was developed, one-stage SGG models based on a one-stage object detector have been actively studied. However,…

Speculative decoding (SD) accelerates Large Language Model (LLM) generation by using an efficient draft model to propose the next few tokens, which are verified by the LLM in a single forward call, reducing latency while preserving its…

How can robots learn dexterous grasping skills efficiently and apply them adaptively based on user instructions? This work tackles two key challenges: efficient skill acquisition from limited human demonstrations and context-driven skill…

Although deep reinforcement learning (DRL) algorithms have made important achievements in many control tasks, they still suffer from the problems of sample inefficiency and unstable training process, which are usually caused by sparse…

Previous studies on event camera sensing have demonstrated certain detection performance using dense event representations. However, the accumulated noise in such dense representations has received insufficient attention, which degrades the…

Sampling-based motion planning (SBMP) algorithms are renowned for their robust global search capabilities. However, the inherent randomness in their sampling mechanisms often result in inconsistent path quality and limited search…

The recently proposed DEtection TRansformer (DETR) has established a fully end-to-end paradigm for object detection. However, DETR suffers from slow training convergence, which hinders its applicability to various detection tasks. We…

Sample selection improves the efficiency and effectiveness of machine learning models by providing informative and representative samples. Typically, samples can be modeled as a sample graph, where nodes are samples and edges represent…

We present in this paper a novel denoising training method to speedup DETR (DEtection TRansformer) training and offer a deepened understanding of the slow convergence issue of DETR-like methods. We show that the slow convergence results…

Deep learning has led to great progress in the detection of mobile (i.e. movement-capable) objects in urban driving scenes in recent years. Supervised approaches typically require the annotation of large training sets; there has thus been…

Synthesizing information from multiple data sources is crucial for constructing accurate individualized treatment rules (ITRs). However, privacy concerns often present significant barriers to the integrative analysis of such multi-source…

Predicting pedestrian behavior is challenging yet crucial for applications such as autonomous driving and smart city. Recent deep learning models have achieved remarkable performance in making accurate predictions, but they fail to provide…

While training on samples drawn from independent and identical distribution has been a de facto paradigm for optimizing image classification networks, humans learn new concepts in an easy-to-hard manner and on the selected examples…

Although the anchor-based detectors have taken a big step forward in pedestrian detection, the overall performance of algorithm still needs further improvement for practical applications, \emph{e.g.}, a good trade-off between the accuracy…

Compared with the generic scenes, crowded scenes contain highly-overlapped instances, which result in: 1) more ambiguous anchors during training of object detectors, and 2) more predictions are likely to be mistakenly suppressed in…

In this paper, we propose a novel SpatioTemporal convolutional Dense Network (STDNet) to address the video-based crowd counting problem, which contains the decomposition of 3D convolution and the 3D spatiotemporal dilated dense convolution…

Spatial Transformer Networks (STN) can generate geometric transformations which modify input images to improve the classifier's performance. In this work, we combine the idea of STN with Reinforcement Learning (RL). To this end, we break…

Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise. Through an empirical study, we observe that responses with medium…

In this report, we present RT-DETRv2, an improved Real-Time DEtection TRansformer (RT-DETR). RT-DETRv2 builds upon the previous state-of-the-art real-time detector, RT-DETR, and opens up a set of bag-of-freebies for flexibility and…