Related papers: DistillMatch: Leveraging Knowledge Distillation fr…

State-of-the-art CNN based recognition models are often computationally prohibitive to deploy on low-end devices. A promising high level approach tackling this limitation is knowledge distillation, which let small student model mimic…

Pedestrian trajectory forecasting is crucial in various applications such as autonomous driving and mobile robot navigation. In such applications, camera-based perception enables the extraction of additional modalities (human pose, text) to…

Recent advances in multimodal learning have achieved remarkable success across diverse vision-language tasks. However, such progress heavily relies on large-scale image-text datasets, making training costly and inefficient. Prior efforts in…

Frame-wise semantic segmentation of indoor lidar scans is a fundamental step toward higher-level 3D scene understanding and mapping applications. However, acquiring frame-wise ground truth for training deep learning models is costly and…

Vision foundation models trained via multi-teacher distillation offer a promising path toward unified visual representations, yet the learning dynamics and data efficiency of such approaches remain underexplored. In this paper, we…

The utilization of multi-modal sensor data in visual place recognition (VPR) has demonstrated enhanced performance compared to single-modal counterparts. Nonetheless, integrating additional sensors comes with elevated costs and may not be…

Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances, overshadowing previous prevalent pre-training approaches such as image classification, instance contrastive learning, and image-text…

Recent advances in deep learning has lead to rapid developments in the field of image retrieval. However, the best performing architectures incur significant computational cost. Recent approaches tackle this issue using knowledge…

Human Activity Recognition is an important task in many human-computer collaborative scenarios, whilst having various practical applications. Although uni-modal approaches have been extensively studied, they suffer from data quality and…

Knowledge distillation is an effective method to improve the performance of a lightweight neural network (i.e., student model) by transferring the knowledge of a well-performed neural network (i.e., teacher model), which has been widely…

We propose a novel knowledge distillation approach, CustomKD, that effectively leverages large vision foundation models (LVFMs) to enhance the performance of edge models (e.g., MobileNetV3). Despite recent advancements in LVFMs, such as…

We propose a cross-modal attention distillation framework to train a dual-encoder model for vision-language understanding tasks, such as visual reasoning and visual question answering. Dual-encoder models have a faster inference speed than…

Multimodal transfer learning aims to transform pretrained representations of diverse modalities into a common domain space for effective multimodal fusion. However, conventional systems are typically built on the assumption that all…

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…

Past works on multimodal machine translation (MMT) elevate bilingual setup by incorporating additional aligned vision information. However, an image-must requirement of the multimodal dataset largely hinders MMT's development -- namely that…

Many recommender models have been proposed to investigate how to incorporate multimodal content information into traditional collaborative filtering framework effectively. The use of multimodal information is expected to provide more…

Knowledge distillation (KD) has been widely applied in semantic segmentation to compress large models, but conventional approaches primarily preserve in-domain accuracy while neglecting out-of-domain generalization, which is essential under…

Dataset distillation aims to synthesize a small dataset from a large dataset, enabling the model trained on it to perform well on the original dataset. With the blooming of large language models and multimodal large language models, the…

Knowledge Distillation is crucial for optimizing face recognition models for deployment in computationally limited settings, such as edge devices. Traditional KD methods, such as Raw L2 Feature Distillation or Feature Consistency loss,…

Continual learning focuses on incrementally training a model on a sequence of tasks with the aim of learning new tasks while minimizing performance drop on previous tasks. Existing approaches at the intersection of Continual Learning and…