Related papers: Online Visual Tracking with One-Shot Context-Aware…

Appearance changes due to weather and seasonal conditions represent a strong impediment to the robust implementation of machine learning systems in outdoor robotics. While supervised learning optimises a model for the training domain, it…

Contextual bandit algorithms are essential for solving real-world decision making problems. In practice, collecting a contextual bandit's feedback from different domains may involve different costs. For example, measuring drug reaction from…

We propose Domain-Conditioned Meta-Contrastive Learning, a framework for improving the cross-domain generalization of vision-language models. While contrastive models such as CLIP achieve strong performance through large-scale training,…

Object detection algorithms allow to enable many interesting applications which can be implemented in different devices, such as smartphones and wearable devices. In the context of a cultural site, implementing these algorithms in a…

Recently, Siamese networks have drawn great attention in visual tracking community because of their balanced accuracy and speed. However, features used in most Siamese tracking approaches can only discriminate foreground from the…

Accurate real depth annotations are difficult to acquire, needing the use of special devices such as a LiDAR sensor. Self-supervised methods try to overcome this problem by processing video or stereo sequences, which may not always be…

LiDAR semantic segmentation provides 3D semantic information about the environment, an essential cue for intelligent systems during their decision making processes. Deep neural networks are achieving state-of-the-art results on large public…

Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data. Unsupervised Domain Adaptation (UDA) is a promising approach to adapt models for new…

Domain adaptation is one of the prominent strategies for handling both domain shift, that is widely encountered in large-scale land use/land cover map calculation, and the scarcity of pixel-level ground truth that is crucial for supervised…

Long-Term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics due to season, illumination variance, etc. Image retrieval for localization is an efficient and effective solution…

The current strive towards end-to-end trainable computer vision systems imposes major challenges for the task of visual tracking. In contrast to most other vision problems, tracking requires the learning of a robust target-specific…

The standard closed-set domain adaptation approaches seek to mitigate distribution discrepancies between two domains under the constraint of both sharing identical label sets. However, in realistic scenarios, finding an optimal source…

Semantic segmentation has achieved significant advances in recent years. While deep neural networks perform semantic segmentation well, their success rely on pixel level supervision which is expensive and time-consuming. Further, training…

There is growing interest in object detection in advanced driver assistance systems and autonomous robots and vehicles. To enable such innovative systems, we need faster object detection. In this work, we investigate the trade-off between…

Visual Domain Adaptation is a problem of immense importance in computer vision. Previous approaches showcase the inability of even deep neural networks to learn informative representations across domain shift. This problem is more severe…

The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…

3D object detectors are fundamental components of perception systems in autonomous vehicles. While these detectors achieve remarkable performance on standard autonomous driving benchmarks, they often struggle to generalize across different…

Visual tracking addresses the problem of identifying and localizing an unknown target in a video given the target specified by a bounding box in the first frame. In this paper, we propose a dual network to better utilize features among…

Real world applications of stereo depth estimation require models that are robust to dynamic variations in the environment. Even though deep learning based stereo methods are successful, they often fail to generalize to unseen variations in…

Semantic segmentation, a pixel-level vision task, is developed rapidly by using convolutional neural networks (CNNs). Training CNNs requires a large amount of labeled data, but manually annotating data is difficult. For emancipating…