Related papers: D$^{2}$-VPR: A Parameter-efficient Visual-foundati…
Traditional visual place recognition (VPR), usually using standard cameras, is easy to fail due to glare or high-speed motion. By contrast, event cameras have the advantages of low latency, high temporal resolution, and high dynamic range,…
Visual Place Recognition (VPR) is a key component for localisation in GNSS-denied environments, but its performance critically depends on selecting an image matching threshold (operating point) that balances precision and recall. Thresholds…
Deep learning methods for Visual Place Recognition (VPR) have advanced significantly, largely driven by large-scale datasets. However, most existing approaches are trained on a single dataset, which can introduce dataset-specific inductive…
The visual-question localized-answering (VQLA) system can serve as a knowledgeable assistant in surgical education. Except for providing text-based answers, the VQLA system can highlight the interested region for better surgical scene…
Low-overhead visual place recognition (VPR) is a highly active research topic. Mobile robotics applications often operate under low-end hardware, and even more hardware capable systems can still benefit from freeing up onboard system…
Vision-Language Models (VLMs) demonstrate remarkable zero-shot generalization to unseen tasks, but fall short of the performance of supervised methods in generalizing to downstream tasks with limited data. Prompt learning is emerging as a…
Visual Place Recognition (VPR) is a crucial component of many visual localization pipelines for embodied agents. VPR is often formulated as an image retrieval task aimed at jointly learning local features and an aggregation method. The…
Visual place recognition (VPR) is an essential component of robot navigation and localization systems that allows them to identify a place using only image data. VPR is challenging due to the significant changes in a place's appearance…
Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR). In this paper, we aim to improve distillation methods that pave the way for the resource-efficient deployment of such models in…
Dataset distillation (DD) compresses a large training set into a small synthetic set, reducing storage and training cost, and has shown strong results on general benchmarks. Decoupled DD further improves efficiency by splitting the pipeline…
The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real samples. Existing distillation methods…
Vision foundation models are renowned for the generalization ability due to massive training data. Nevertheless, they demand tremendous training resources, and the training data is often inaccessible, e.g., CLIP, DINOv2, posing great…
Vision-Language Pre-training (VLP) shows remarkable progress with the assistance of extremely heavy parameters, which challenges deployment in real applications. Knowledge distillation is well recognized as the essential procedure in model…
Vision Foundation Models (VFMs) have achieved remarkable success when applied to various downstream 2D tasks. Despite their effectiveness, they often exhibit a critical lack of 3D awareness. To this end, we introduce Splat and Distill, a…
Fine-Grained Image Retrieval~(FGIR) faces challenges in learning discriminative visual representations to retrieve images with similar fine-grained features. Current leading FGIR solutions typically follow two regimes: enforce pairwise…
Visual place recognition (VPR) is an essential component of robot navigation and localization systems that allows them to identify a place using only image data. VPR is challenging due to the significant changes in a place's appearance…
The detection of objects considering a 6DoF pose is a common requirement to build virtual and augmented reality applications. It is usually a complex task which requires real-time processing and high precision results for adequate user…
Knowledge distillation (KD) is a valuable yet challenging approach that enhances a compact student network by learning from a high-performance but cumbersome teacher model. However, previous KD methods for image restoration overlook the…
Visual Place Recognition (VPR) in dynamic and perceptually aliased environments remains a fundamental challenge for long-term localization. Existing deep learning-based solutions predominantly focus on single-frame embeddings, neglecting…
Knowledge distillation is a popular technique for transferring the knowledge from a large teacher model to a smaller student model by mimicking. However, distillation by directly aligning the feature maps between teacher and student may…