Related papers: Cloud-Device Collaborative Adaptation to Continual…
Technological advancements have led to the rise of wearable devices with sensors that continuously monitor user activities, generating vast amounts of unlabeled data. This data is challenging to interpret, and manual annotation is…
Unsupervised Domain Adaptation transfers knowledge from a labeled source domain to an unlabeled target domain. Directly deploying Vision-Language Models (VLMs) with prompt tuning in downstream UDA tasks faces the signifi cant challenge of…
Recently, large-scale pre-trained vision-language models (e.g. CLIP and ALIGN) have demonstrated remarkable effectiveness in acquiring transferable visual representations. To leverage the valuable knowledge encoded within these models for…
A hybrid mobile/fixed device cloud that harnesses sensing, computing, communication, and storage capabilities of mobile and fixed devices in the field as well as those of computing and storage servers in remote datacenters is envisioned.…
Unsupervised Domain Adaptation (UDA) is a critical challenge in real-world vision systems, especially in resource-constrained environments like drones, where memory and computation are limited. Existing prompt-driven UDA methods typically…
Prompt learning has emerged as an efficient and effective approach for transferring foundational Vision-Language Models (e.g., CLIP) to downstream tasks. However, current methods tend to overfit to seen categories, thereby limiting their…
AI deployed in the real-world should be capable of autonomously adapting to novelties encountered after deployment. Yet, in the field of continual learning, the reliance on novelty and labeling oracles is commonplace albeit unrealistic.…
This work focuses on the question of learning from a large number of devices with each device holding only a single sample of data. Several real-world applications exist to this one sample per client setup up including learning from fitness…
Navigating autonomous vehicles in open scenarios is a challenge due to the difficulties in handling unseen objects. Existing solutions either rely on small models that struggle with generalization or large models that are…
Video Correlation Learning (VCL), which aims to analyze the relationships between videos, has been widely studied and applied in various general video tasks. However, applying VCL to instructional videos is still quite challenging due to…
Predicting future resource demand in Cloud Computing is essential for optimizing the trade-off between serving customers' requests efficiently and minimizing the provisioning cost. Modelling prediction uncertainty is also desirable to…
Recent advancements in deep models have highlighted the need for intelligent systems that combine continual learning (CL) for knowledge acquisition with machine unlearning (MU) for data removal, forming the Continual Learning-Unlearning…
Visual question answering (VQA) is crucial for promoting surgical education. In practice, the needs of trainees are constantly evolving, such as learning more surgical types, adapting to different robots, and learning new surgical…
Currently, the divergence in distributions of design and operational data, and large computational complexity are limiting factors in the adoption of CNNs in real-world applications. For instance, person re-identification systems typically…
Vision-Language Models (VLMs) demonstrate impressive zero-shot generalization through large-scale image-text pretraining, yet their performance can drop once the deployment distribution diverges from the training distribution. To address…
Addressing the challenge of domain shift between datasets is vital in maintaining model performance. In the context of cross-domain object detection, the teacher-student framework, a widely-used semi-supervised model, has shown significant…
Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…
Cloud-based software systems are increasingly becoming complex and operating in highly dynamic environments. Self-adaptivity and self-awareness have recently emerged to cope with such level of dynamicity and scalability. Meanwhile,…
Unsupervised pre-training approaches have achieved great success in many fields such as Computer Vision (CV), Natural Language Processing (NLP) and so on. However, compared to typical deep learning models, pre-training or even fine-tuning…
Diffusion models have become a powerful backbone for text-to-image generation, producing high-quality visuals from natural language prompts. However, when prompts involve multiple objects alongside global or local style instructions, the…