Related papers: Curiosity-driven 3D Object Detection Without Label…

Object detectors often experience a drop in performance when new environmental conditions are insufficiently represented in the training data. This paper studies how to automatically fine-tune a pre-existing object detector while exploring…

We show that it is possible to learn semantic segmentation from very limited amounts of manual annotations, by enforcing geometric 3D constraints between multiple views. More exactly, image locations corresponding to the same physical 3D…

We propose real-time, six degrees of freedom (6DoF), 3D face pose estimation without face detection or landmark localization. We observe that estimating the 6DoF rigid transformation of a face is a simpler problem than facial landmark…

We present BlockGAN, an image generative model that learns object-aware 3D scene representations directly from unlabelled 2D images. Current work on scene representation learning either ignores scene background or treats the whole scene as…

3D object detection from monocular images is an ill-posed problem due to the projective entanglement of depth and scale. To overcome this ambiguity, we present a novel self-supervised method for textured 3D shape reconstruction and pose…

Semantic segmentation of 3D LiDAR point clouds, essential for autonomous driving and infrastructure management, is best achieved by supervised learning, which demands extensive annotated datasets and faces the problem of domain shifts. We…

Monocular 3D object detection is one of the most challenging tasks in 3D scene understanding. Due to the ill-posed nature of monocular imagery, existing monocular 3D detection methods highly rely on training with the manually annotated 3D…

In recent years, the performance of object detection has advanced significantly with the evolving deep convolutional neural networks. However, the state-of-the-art object detection methods still rely on accurate bounding box annotations…

Current 3D scene segmentation methods are heavily dependent on manually annotated 3D training datasets. Such manual annotations are labor-intensive, and often lack fine-grained details. Importantly, models trained on this data typically…

Detecting objects in 3D space using multiple cameras, known as Multi-Camera 3D Object Detection (MC3D-Det), has gained prominence with the advent of bird's-eye view (BEV) approaches. However, these methods often struggle when faced with…

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i.e., without using…

We propose a new approach, Synthetic Optimized Layout with Instance Detection (SOLID), to pretrain object detectors with synthetic images. Our "SOLID" approach consists of two main components: (1) generating synthetic images using a…

Learning object detectors requires massive amounts of labeled training samples from the specific data source of interest. This is impractical when dealing with many different sources (e.g., in camera networks), or constantly changing ones…

Without the demand of training in reality, humans can easily detect a known concept simply based on its language description. Empowering deep learning with this ability undoubtedly enables the neural network to handle complex vision tasks,…

We propose a method for learning landmark detectors for visual objects (such as the eyes and the nose in a face) without any manual supervision. We cast this as the problem of generating images that combine the appearance of the object as…

Being able to segment unseen classes not observed during training is an important technical challenge in deep learning, because of its potential to reduce the expensive annotation required for semantic segmentation. Prior zero-label…

Existing deep learning based unsupervised video object segmentation methods still rely on ground-truth segmentation masks to train. Unsupervised in this context only means that no annotated frames are used during inference. As obtaining…

Training a deep object detector for autonomous driving requires a huge amount of labeled data. While recording data via on-board sensors such as camera or LiDAR is relatively easy, annotating data is very tedious and time-consuming,…

Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed set of classes, and fail when facing novel elements, also…

Learning to localize objects with minimal supervision is an important problem in computer vision, since large fully annotated datasets are extremely costly to obtain. In this paper, we propose a new method that achieves this goal with only…