Related papers: Multiscale Vision Transformers meet Bipartite Matc…

Semantic understanding and localization are fundamental enablers of robot autonomy that have for the most part been tackled as disjoint problems. While deep learning has enabled recent breakthroughs across a wide spectrum of scene…

The recently-developed DETR approach applies the transformer encoder and decoder architecture to object detection and achieves promising performance. In this paper, we handle the critical issue, slow training convergence, and present a…

There have been two streams in the 3D detection from point clouds: single-stage methods and two-stage methods. While the former is more computationally efficient, the latter usually provides better detection accuracy. By carefully examining…

In this paper, we address the problem of Multiple Transmitter Localization (MTL). MTL is to determine the locations of potential multiple transmitters in a field, based on readings from a distributed set of sensors. In contrast to the…

Human pose estimation and action recognition are related tasks since both problems are strongly dependent on the human body representation and analysis. Nonetheless, most recent methods in the literature handle the two problems separately.…

We study the problem of multi-robot active mapping, which aims for complete scene map construction in minimum time steps. The key to this problem lies in the goal position estimation to enable more efficient robot movements. Previous…

Autonomous driving requires the inference of actionable information such as detecting and classifying objects, and determining the drivable space. To this end, we present Multi-View LidarNet (MVLidarNet), a two-stage deep neural network for…

Transfer learning is widely used in computer vision (CV), natural language processing (NLP) and achieves great success. Most transfer learning systems are based on the same modality (e.g. RGB image in CV and text in NLP). However, the…

The real-world data tends to be heavily imbalanced and severely skew the data-driven deep neural networks, which makes Long-Tailed Recognition (LTR) a massive challenging task. Existing LTR methods seldom train Vision Transformers (ViTs)…

Vision Transformers (ViTs) are built by stacking independently parameterized blocks, but it remains unclear how much of this depth requires layer specific transformations and how much can be realized through recurrent computation. We study…

Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning…

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…

Transformers have become the standard in state-of-the-art vision architectures, achieving impressive performance on both image-level and dense pixelwise tasks. However, training vision transformers for high-resolution pixelwise tasks has a…

Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures…

With the advent of large language models and large-scale robotic datasets, there has been tremendous progress in high-level decision-making for object manipulation. These generic models are able to interpret complex tasks using language…

Vision language models (VLMs) have seen growing adoption in recent years, but many still struggle with basic spatial reasoning errors. We hypothesize that this is due to VLMs adopting pre-trained vision backbones, specifically vision…

Vision-language pre-training (VLP) on large-scale image-text pairs has achieved huge success for the cross-modal downstream tasks. The most existing pre-training methods mainly adopt a two-step training procedure, which firstly employs a…

As Vision Transformers (ViTs) increasingly set new benchmarks in computer vision, their practical deployment on inference engines is often hindered by their significant memory bandwidth and (on-chip) memory footprint requirements. This…

Built on top of self-attention mechanisms, vision transformers have demonstrated remarkable performance on a variety of vision tasks recently. While achieving excellent performance, they still require relatively intensive computational cost…

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects across video frames. Detection boxes serve as the basis of both 2D and 3D MOT. The inevitable changing of detection scores leads to object missing after…