Related papers: AttentionMask: Attentive, Efficient Object Proposa…

Weakly supervised methods usually generate localization results based on attention maps produced by classification networks. However, the attention maps exhibit the most discriminative parts of the object which are small and sparse. We…

Model efficiency has become increasingly important in computer vision. In this paper, we systematically study neural network architecture design choices for object detection and propose several key optimizations to improve efficiency.…

We propose a novel recurrent attentional structure to localize and recognize objects jointly. The network can learn to extract a sequence of local observations with detailed appearance and rough context, instead of sliding windows or…

We present Attention Mesh, a lightweight architecture for 3D face mesh prediction that uses attention to semantically meaningful regions. Our neural network is designed for real-time on-device inference and runs at over 50 FPS on a Pixel 2…

3D point cloud segmentation has a wide range of applications in areas such as autonomous driving, augmented reality, virtual reality and digital twins. The point cloud data collected in real scenes often contain small objects and categories…

Fully supervised object detection has achieved great success in recent years. However, abundant bounding boxes annotations are needed for training a detector for novel classes. To reduce the human labeling effort, we propose a novel webly…

Recognizing the category of the object and using the features of the object itself to predict grasp configuration is of great significance to improve the accuracy of the grasp detection model and expand its application. Researchers have…

A dominant paradigm for deep learning based object detection relies on a "bottom-up" approach using "passive" scoring of class agnostic proposals. These approaches are efficient but lack of holistic analysis of scene-level context. In this…

Learning object-centric representations of complex scenes is a promising step towards enabling efficient abstract reasoning from low-level perceptual features. Yet, most deep learning approaches learn distributed representations that do not…

Advances in lightweight neural networks have revolutionized computer vision in a broad range of IoT applications, encompassing remote monitoring and process automation. However, the detection of small objects, which is crucial for many of…

Most of existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately. However, the important semantic and spatial layout correlations among proposals are…

Many object detection models struggle with several problematic aspects of small object detection including the low number of samples, lack of diversity and low features representation. Taking into account that GANs belong to generative…

Recent object detection methods have made remarkable progress by leveraging attention mechanisms to improve feature discriminability. However, most existing approaches are confined to refining single-layer or fusing dual-layer features,…

Recent cutting-edge feature aggregation paradigms for video object detection rely on inferring feature correspondence. The feature correspondence estimation problem is fundamentally difficult due to poor image quality, motion blur, etc, and…

Tiny object detection is one of the key challenges in the field of object detection. The performance of most generic detectors dramatically decreases in tiny object detection tasks. The main challenge lies in extracting effective features…

Image-to-video adaptation seeks to efficiently adapt image models for use in the video domain. Instead of finetuning the entire image backbone, many image-to-video adaptation paradigms use lightweight adapters for temporal modeling on top…

A major impediment in rapidly deploying object detection models for instance detection is the lack of large annotated datasets. For example, finding a large labeled dataset containing instances in a particular kitchen is unlikely. Each new…

The standard content-based attention mechanism typically used in sequence-to-sequence models is computationally expensive as it requires the comparison of large encoder and decoder states at each time step. In this work, we propose an…

3D object detection is an essential vision technique for various robotic systems, such as augmented reality and domestic robots. Transformers as versatile network architectures have recently seen great success in 3D point cloud object…

We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes. The key of our approach is to let each proposal predict a set of correlated instances rather than a single…