Related papers: Enhancing Your Trained DETRs with Box Refinement

In this report, we introduce the technical details of our submission to the VIPriors object detection challenge. Our solution is based on mmdetction of a strong baseline open-source detection toolbox. Firstly, we introduce an effective data…

Despite previous DETR-like methods having performed successfully in generic object detection, tiny object detection is still a challenging task for them since the positional information of object queries is not customized for detecting tiny…

Recent research demonstrates the effectiveness of using fine-tuned language models~(LM) for dense retrieval. However, dense retrievers are hard to train, typically requiring heavily engineered fine-tuning pipelines to realize their full…

Modeling sparse and dense image matching within a unified functional correspondence model has recently attracted increasing research interest. However, existing efforts mainly focus on improving matching accuracy while ignoring its…

Recent advances in deep learning greatly boost the performance of object detection. State-of-the-art methods such as Faster-RCNN, FPN and R-FCN have achieved high accuracy in challenging benchmark datasets. However, these methods require…

Efficient fine-tuning of pre-trained Text-to-Image (T2I) models involves adjusting the model to suit a particular task or dataset while minimizing computational resources and limiting the number of trainable parameters. However, it often…

The combination of deep neural nets and theory-driven models, which we call deep grey-box modeling, can be inherently interpretable to some extent thanks to the theory backbone. Deep grey-box models are usually learned with a regularized…

In this paper, we propose a novel query design for the transformer-based object detection. In previous transformer-based detectors, the object queries are a set of learned embeddings. However, each learned embedding does not have an…

Reachable set computation is an important tool for analyzing control systems. Simulating a control system can show general trends, but a formal tool like reachability analysis can provide guarantees of correctness. Reachability analysis for…

Deep learning models for image compression often face practical limitations in hardware-constrained applications. Although these models achieve high-quality reconstructions, they are typically complex, heavyweight, and require substantial…

Much recent progress has been made in reconstructing the 3D shape of an object from an image of it, i.e. single view 3D reconstruction. However, it has been suggested that current methods simply adopt a "nearest-neighbor" strategy, instead…

We present a novel method for local image feature matching. Instead of performing image feature detection, description, and matching sequentially, we propose to first establish pixel-wise dense matches at a coarse level and later refine the…

Object detection is an import task of computer vision.A variety of methods have been proposed,but methods using the weak labels still do not have a satisfactory result.In this paper,we propose a new framework that using the weakly…

Recently, numerous methods have achieved impressive performance in remote sensing object detection, relying on convolution or transformer architectures. Such detectors typically have a feature backbone to extract useful features from raw…

DETR accomplishes end-to-end object detection through iteratively generating multiple object candidates based on image features and promoting one candidate for each ground-truth object. The traditional training procedure using one-to-one…

Object detection is a fundamental task for robots to operate in unstructured environments. Today, there are several deep learning algorithms that solve this task with remarkable performance. Unfortunately, training such systems requires…

Optimizing the noise samples of diffusion and flow models is an increasingly popular approach to align these models to target rewards at inference time. However, we observe that these approaches are usually restricted to differentiable or…

We present an endpoint box regression module(epBRM), which is designed for predicting precise 3D bounding boxes using raw LiDAR 3D point clouds. The proposed epBRM is built with sequence of small networks and is computationally lightweight.…

Dense Retrieval (DR) has achieved state-of-the-art first-stage ranking effectiveness. However, the efficiency of most existing DR models is limited by the large memory cost of storing dense vectors and the time-consuming nearest neighbor…

Albeit revealing impressive predictive performance for several computer vision tasks, deep neural networks (DNNs) are prone to making overconfident predictions. This limits the adoption and wider utilization of DNNs in many safety-critical…