Related papers: Supervision by Registration and Triangulation for …
The rapid development of 3D object detection systems for self-driving cars has significantly improved accuracy. However, these systems struggle to generalize across diverse driving environments, which can lead to safety-critical failures in…
This paper proposes a method to ease the unsupervised learning of object landmark detectors. Similarly to previous methods, our approach is fully unsupervised in a sense that it does not require or make any use of annotated landmarks for…
With the prosperity of the video surveillance, multiple cameras have been applied to accurately locate pedestrians in a specific area. However, previous methods rely on the human-labeled annotations in every video frame and camera view,…
Sign language recognition (SLR) is a machine learning task aiming to identify signs in videos. Due to the scarcity of annotated data, unsupervised methods like contrastive learning have become promising in this field. They learn meaningful…
Retinal image registration, particularly for color fundus images, is a challenging yet essential task with diverse clinical applications. Existing registration methods for color fundus images typically rely on keypoints and descriptors for…
In some of object recognition problems, labeled data may not be available for all categories. Zero-shot learning utilizes auxiliary information (also called signatures) describing each category in order to find a classifier that can…
Unsupervised retrieval of image features is vital for many computer vision tasks where the annotation is missing or scarce. In this work, we propose a new unsupervised approach to detect the landmarks in images, validating it on the popular…
Unsupervised learning is a challenging task due to the lack of labels. Multiple Object Tracking (MOT), which inevitably suffers from mutual object interference, occlusion, etc., is even more difficult without label supervision. In this…
Tracking segmentation masks of multiple instances has been intensively studied, but still faces two fundamental challenges: 1) the requirement of large-scale, frame-wise annotation, and 2) the complexity of two-stage approaches. To resolve…
Supervised contour detection methods usually require many labeled training images to obtain satisfactory performance. However, a large set of annotated data might be unavailable or extremely labor intensive. In this paper, we investigate…
For a self-driving car to operate reliably, its perceptual system must generalize to the end-user's environment -- ideally without additional annotation efforts. One potential solution is to leverage unlabeled data (e.g., unlabeled LiDAR…
Terrain awareness, i.e., the ability to identify and distinguish different types of terrain, is a critical ability that robots must have to succeed at autonomous off-road navigation. Current approaches that provide robots with this…
We present two techniques to improve landmark localization in images from partially annotated datasets. Our primary goal is to leverage the common situation where precise landmark locations are only provided for a small data subset, but…
Multi-label Recognition (MLR) involves assigning multiple labels to each data instance in an image, offering advantages over single-label classification in complex scenarios. However, it faces the challenge of annotating all relevant…
In this paper we propose a strategy for semi-supervised image classification that leverages unsupervised representation learning and co-training. The strategy, that is called CURL from Co-trained Unsupervised Representation Learning,…
Designing learning-based no-reference (NR) video quality assessment (VQA) algorithms for camera-captured videos is cumbersome due to the requirement of a large number of human annotations of quality. In this work, we propose a…
Self-supervised learning (SSL) can be used to solve complex visual tasks without human labels. Self-supervised representations encode useful semantic information about images, and as a result, they have already been used for tasks such as…
Self-supervised learning allows for better utilization of unlabelled data. The feature representation obtained by self-supervision can be used in downstream tasks such as classification, object detection, segmentation, and anomaly…
Semi-supervised segmentation tackles the scarcity of annotations by leveraging unlabeled data with a small amount of labeled data. A prominent way to utilize the unlabeled data is by consistency training which commonly uses a…
We present a conceptually simple self-supervised method for saliency detection. Our method generates and uses pseudo-ground truth labels for training. The generated pseudo-GT labels don't require any kind of human annotations (e.g.,…