Related papers: LeMoRe: Learn More Details for Lightweight Semanti…
Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are…
Both Convolutional Neural Networks (CNNs) and Transformers have shown great success in semantic segmentation tasks. Efforts have been made to integrate CNNs with Transformer models to capture both local and global context interactions.…
For real-time semantic segmentation, how to increase the speed while maintaining high resolution is a problem that has been discussed and solved. Backbone design and fusion design have always been two essential parts of real-time semantic…
Semantic labelling is highly correlated with geometry and radiance reconstruction, as scene entities with similar shape and appearance are more likely to come from similar classes. Recent implicit neural reconstruction techniques are…
We introduce a deep learning image segmentation framework that is extremely robust to missing imaging modalities. Instead of attempting to impute or synthesize missing data, the proposed approach learns, for each modality, an embedding of…
Real-time semantic segmentation plays an important role in practical applications such as self-driving and robots. Most semantic segmentation research focuses on improving estimation accuracy with little consideration on efficiency. Several…
Large vision-language models (LVLMs) are typically trained using autoregressive language modeling objectives, which align visual representations with linguistic space. While effective for multimodal reasoning, this alignment can weaken…
Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…
Due to real-time image semantic segmentation needs on power constrained edge devices, there has been an increasing desire to design lightweight semantic segmentation neural network, to simultaneously reduce computational cost and increase…
Semantic segmentation is applied extensively in autonomous driving and intelligent transportation with methods that highly demand spatial and semantic information. Here, an STDC-MA network is proposed to meet these demands. First, the…
Semantic image segmentation is an important computer vision task that is difficult because it consists of both recognition and segmentation. The task is often cast as a structured output problem on an exponentially large output-space, which…
Many autonomous robotic applications require object-level understanding when deployed. Actively reconstructing objects of interest, i.e. objects with specific semantic meanings, is therefore relevant for a robot to perform downstream tasks…
Semantic segmentation benefits robotics related applications especially autonomous driving. Most of the research on semantic segmentation is only on increasing the accuracy of segmentation models with little attention to computationally…
Motion segmentation in dynamic scenes is highly challenging, as conventional methods heavily rely on estimating camera poses and point correspondences from inherently noisy motion cues. Existing statistical inference or iterative…
Real-time object detection has achieved substantial progress through meticulously designed architectures and optimization strategies. However, the pursuit of high-speed inference via lightweight network designs often leads to degraded…
Homography estimation is often an indispensable step in many computer vision tasks. The existing approaches, however, are not robust to illumination and/or larger viewpoint changes. In this paper, we propose bidirectional implicit…
Deep neural networks have achieved remarkable success in computer vision; however, their black-box nature in decision-making limits interpretability and trust, particularly in safety-critical applications. Interpretability is crucial in…
To autonomously navigate and plan interactions in real-world environments, robots require the ability to robustly perceive and map complex, unstructured surrounding scenes. Besides building an internal representation of the observed scene…
In this study, we introduce EdgeSegNet, a compact deep convolutional neural network for the task of semantic segmentation. A human-machine collaborative design strategy is leveraged to create EdgeSegNet, where principled network design…
With the proliferation of edge computing, efficient AI inference on edge devices has become essential for intelligent applications such as autonomous vehicles and VR/AR. In this context, we address the problem of efficient remote object…