Related papers: DistilVPR: Cross-Modal Knowledge Distillation for …
In the surveillance and defense domain, multi-target detection and classification (MTD) is considered essential yet challenging due to heterogeneous inputs from diverse data sources and the computational complexity of algorithms designed…
Person re-identification is a key challenge for surveillance across multiple sensors. Prompted by the advent of powerful deep learning models for visual recognition, and inexpensive RGB-D cameras and sensor-rich mobile robotic platforms,…
Resource-constrained perception systems such as edge computing and vision-for-robotics require vision models to be both accurate and lightweight in computation and memory usage. While knowledge distillation is a proven strategy to enhance…
We present a hybrid-view-based knowledge distillation framework, termed HVDistill, to guide the feature learning of a point cloud neural network with a pre-trained image network in an unsupervised manner. By exploiting the geometric…
A recent approach to the Visual Place Recognition (VPR) problem has been to fuse the place recognition estimates of multiple complementary VPR techniques simultaneously. However, selecting the optimal set of techniques to use in a specific…
For tasks involving language and vision, the current state-of-the-art methods tend not to leverage any additional information that might be present to gather relevant (commonsense) knowledge. A representative task is Visual Question…
Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations from scratch through reconstructing low-level features like…
Having access to multi-modal cues (e.g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality. In this work, we propose to transfer knowledge across heterogeneous modalities, even…
We present Distill CLIP (DCLIP), a fine-tuned variant of the CLIP model that enhances multimodal image-text retrieval while preserving the original model's strong zero-shot classification capabilities. CLIP models are typically constrained…
Model compression and knowledge distillation have been successfully applied for cross-architecture and cross-domain transfer learning. However, a key requirement is that training examples are in correspondence across the domains. We show…
Recent Knowledge distillation (KD) studies show that different manually designed schemes impact the learned results significantly. Yet, in KD, automatically searching an optimal distillation scheme has not yet been well explored. In this…
Knowledge distillation is an effective method for training small and efficient deep learning models. However, the efficacy of a single method can degenerate when transferring to other tasks, modalities, or even other architectures. To…
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…
Depth estimation and scene segmentation are two important tasks in intelligent transportation systems. A joint modeling of these two tasks will reduce the requirement for both the storage and training efforts. This work explores how the…
Training a small student network with the guidance of a larger teacher network is an effective way to promote the performance of the student. Despite the different types, the guided knowledge used to distill is always kept unchanged for…
Convolutional Neural Networks (CNNs) are prone to overfit small training datasets. We present a novel two-phase pipeline that leverages self-supervised learning and knowledge distillation to improve the generalization ability of CNN models…
Cross-modal contrastive distillation has recently been explored for learning effective 3D representations. However, existing methods focus primarily on modality-shared features, neglecting the modality-specific features during the…
Visual Place Recognition (VPR) is the process of recognising a previously visited place using visual information, often under varying appearance conditions and viewpoint changes and with computational constraints. VPR is related to the…
Visual Place Recognition (VPR) has advanced significantly with high-capacity foundation models like DINOv2, achieving remarkable performance. Nonetheless, their substantial computational cost makes deployment on resource-constrained devices…
Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance. For this purpose, various approaches have been proposed over the past few years,…