Related papers: Curiosity-driven 3D Object Detection Without Label…
Deep convolutional neural networks (CNNs) have demonstrated remarkable success in computer vision by supervisedly learning strong visual feature representations. However, training CNNs relies heavily on the availability of exhaustive…
Deep neural networks can model images with rich latent representations, but they cannot naturally conceptualize structures of object categories in a human-perceptible way. This paper addresses the problem of learning object structures in an…
Object detection is one of the major problems in computer vision, and has been extensively studied. Most of the existing detection works rely on labor-intensive supervision, such as ground truth bounding boxes of objects or at least…
Deep neural networks have exhibited remarkable performance in various domains. However, the reliance of these models on spurious features has raised concerns about their reliability. A promising solution to this problem is last-layer…
Deep learning has attained remarkable success in many 3D visual recognition tasks, including shape classification, object detection, and semantic segmentation. However, many of these results rely on manually collecting densely annotated…
Accurate 3D object detection in real-world environments requires a huge amount of annotated data with high quality. Acquiring such data is tedious and expensive, and often needs repeated effort when a new sensor is adopted or when the…
Deep learning has emerged as an effective solution for solving the task of object detection in images but at the cost of requiring large labeled datasets. To mitigate this cost, semi-supervised object detection methods, which consist in…
We propose an adversarial contextual model for detecting moving objects in images. A deep neural network is trained to predict the optical flow in a region using information from everywhere else but that region (context), while another…
Great labels make great models. However, traditional labeling approaches for tasks like object detection have substantial costs at scale. Furthermore, alternatives to fully-supervised object detection either lose functionality or require…
In this work, we study self-supervised multiple object tracking without using any video-level association labels. We propose to cast the problem of multiple object tracking as learning the frame-wise associations between detections in…
Lane detection has evolved highly functional autonomous driving system to understand driving scenes even under complex environments. In this paper, we work towards developing a generalized computer vision system able to detect lanes without…
This paper presents a novel yet intuitive approach to unsupervised feature learning. Inspired by the human visual system, we explore whether low-level motion-based grouping cues can be used to learn an effective visual representation.…
Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotations for thousands of categories at a large scale. We…
Progress in self-supervised learning has brought strong general image representation learning methods. Yet so far, it has mostly focused on image-level learning. In turn, tasks such as unsupervised image segmentation have not benefited from…
Unsupervised learning from visual data is one of the most difficult challenges in computer vision, being a fundamental task for understanding how visual recognition works. From a practical point of view, learning from unsupervised visual…
In this paper, we study a new representation-learning task, which we termed as disassembling object representations. Given an image featuring multiple objects, the goal of disassembling is to acquire a latent representation, of which each…
LiDAR-based 3D object detection and semantic segmentation are critical tasks in 3D scene understanding. Traditional detection and segmentation methods supervise their models through bounding box labels and semantic mask labels. However,…
To alleviate the cost of obtaining accurate bounding boxes for training today's state-of-the-art object detection models, recent weakly supervised detection work has proposed techniques to learn from image-level labels. However, requiring…
Most model-free visual object tracking methods formulate the tracking task as object location estimation given by a 2D segmentation or a bounding box in each video frame. We argue that this representation is limited and instead propose to…
Embodied agents must detect and localize objects of interest, e.g. traffic participants for self-driving cars. Supervision in the form of bounding boxes for this task is extremely expensive. As such, prior work has looked at unsupervised…