Related papers: Graph Distillation for Action Detection with Privi…
Model distillation aims to distill the knowledge of a complex model into a simpler one. In this paper, we consider an alternative formulation called dataset distillation: we keep the model fixed and instead attempt to distill the knowledge…
Current video models fail as world model as they lack fine-graiend control. General-purpose household robots require real-time fine motor control to handle delicate tasks and urgent situations. In this work, we introduce fine-grained…
The Controller Area Network (CAN) protocol is widely adopted for in-vehicle communication but lacks inherent security mechanisms, making it vulnerable to cyberattacks. This paper introduces KD-GAT, an intrusion detection framework that…
Surgical workflow recognition is vital for automating tasks, supporting decision-making, and training novice surgeons, ultimately improving patient safety and standardizing procedures. However, data corruption can lead to performance…
In this paper, we present a simple yet efficient approach for video representation, called Adversarial Video Distillation (AVD). The key idea is to represent videos by compressing them in the form of realistic images, which can be used in a…
A common dilemma in 3D object detection for autonomous driving is that high-quality, dense point clouds are only available during training, but not testing. We use knowledge distillation to bridge the gap between a model trained on…
Using huge training datasets can be costly and inconvenient. This article explores various data distillation techniques that can reduce the amount of data required to successfully train deep networks. Inspired by recent ideas, we suggest…
Retrieval-augmented generation framework can address the limitations of large language models by enabling real-time knowledge updates for more accurate answers. An efficient way in the training phase of retrieval-augmented models is…
State-of-the-art methods for video action recognition commonly use an ensemble of two networks: the spatial stream, which takes RGB frames as input, and the temporal stream, which takes optical flow as input. In recent work, both of these…
Recommender systems presently utilize vast amounts of data and play a pivotal role in enhancing user experiences. Graph Convolution Networks (GCNs) have surfaced as highly efficient models within the realm of recommender systems due to…
Contemporary segmentation methods are usually based on deep fully convolutional networks (FCNs). However, the layer-by-layer convolutions with a growing receptive field is not good at capturing long-range contexts such as lane markers in…
The development of computer vision solutions for gigapixel images in digital pathology is hampered by significant computational limitations due to the large size of whole slide images. In particular, digitizing biopsies at high resolutions…
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…
Graph, such as citation networks, social networks, and transportation networks, are prevalent in the real world. Graph Neural Networks (GNNs) have gained widespread attention for their robust expressiveness and exceptional performance in…
Action detection aims to localize the starting and ending points of action instances in untrimmed videos, and predict the classes of those instances. In this paper, we make the observation that the outputs of the action detection task can…
In recent years, few-shot action recognition has attracted increasing attention. It generally adopts the paradigm of meta-learning. In this field, overcoming the overlapping distribution of classes and outliers is still a challenging…
Deep ensembles excel in large-scale image classification tasks both in terms of prediction accuracy and calibration. Despite being simple to train, the computation and memory cost of deep ensembles limits their practicability. While some…
Generative models are increasingly able to produce remarkably high quality images and text. The community has developed numerous evaluation metrics for comparing generative models. However, these metrics do not effectively quantify data…
Knowledge distillation constitutes a simple yet effective way to improve the performance of a compact student network by exploiting the knowledge of a more powerful teacher. Nevertheless, the knowledge distillation literature remains…
Deploying deep learning models in clinical practice often requires leveraging multiple data modalities, such as images, text, and structured data, to achieve robust and trustworthy decisions. However, not all modalities are always available…