相关论文: Exploring Target Representations for Masked Autoen…

The emergence of the global COVID-19 pandemic poses new challenges for biometrics. Not only are contactless biometric identification options becoming more important, but face recognition has also recently been confronted with the frequent…

Sampling from pretrained diffusion and flow-matching models typically requires many forward passes to generate diverse and high-fidelity images. Existing distillation methods often rely on multiple auxiliary networks, carefully designed…

Teaching requires distilling a rich category distribution into a small set of informative exemplars. Although prior work shows that humans consider both representativeness and diversity when teaching, the computational principles underlying…

Tiny, causal models are crucial for embedded audio machine learning applications. Model compression can be achieved via distilling knowledge from a large teacher into a smaller student model. In this work, we propose a novel two-step…

Deep learning models for multimodal expression recognition have reached remarkable performance in controlled laboratory environments because of their ability to learn complementary and redundant semantic information. However, these models…

Training models continually to detect and classify objects, from new classes and new domains, remains an open problem. In this work, we conduct a thorough analysis of why and how object detection models forget catastrophically. We focus on…

Deep audio representation learning using multi-modal audio-visual data often leads to a better performance compared to uni-modal approaches. However, in real-world scenarios both modalities are not always available at the time of inference,…

In stereo matching, CNNs have traditionally served as the predominant architectures. Although Transformer-based stereo models have been studied recently, their performance still lags behind CNN-based stereo models due to the inherent data…

A key challenge with procedure planning in instructional videos lies in how to handle a large decision space consisting of a multitude of action types that belong to various tasks. To understand real-world video content, an AI agent must…

We present a new method to learn video representations from unlabeled data. Given large-scale unlabeled video data, the objective is to benefit from such data by learning a generic and transferable representation space that can be directly…

Knowledge distillation methods have recently shown to be a promising direction to speedup the synthesis of large-scale diffusion models by requiring only a few inference steps. While several powerful distillation methods were recently…

Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…

We address the challenge of getting efficient yet accurate recognition systems with limited labels. While recognition models improve with model size and amount of data, many specialized applications of computer vision have severe resource…

As an important component of multimedia analysis tasks, audio classification aims to discriminate between different audio signal types and has received intensive attention due to its wide applications. Generally speaking, the raw signal can…

Neural dialogue models suffer from low-quality responses when interacted in practice, demonstrating difficulty in generalization beyond training data. Recently, knowledge distillation has been used to successfully regularize the student by…

Self-supervised learning has emerged as a powerful approach for leveraging large-scale unlabeled data to improve model performance in various domains. In this paper, we explore masked self-supervised pre-training for text recognition…

Knowledge distillation becomes a de facto standard to improve the performance of small neural networks. Most of the previous works propose to regress the representational features from the teacher to the student in a one-to-one spatial…

Pre-trained speech language models such as HuBERT and WavLM leverage unlabeled speech data for self-supervised learning and offer powerful representations for numerous downstream tasks. Despite the success of these models, their high…

This paper explores three novel approaches to improve the performance of speaker verification (SV) systems based on deep neural networks (DNN) using Multi-head Self-Attention (MSA) mechanisms and memory layers. Firstly, we propose the use…

Point cloud understanding aims to acquire robust and general feature representations from unlabeled data. Masked point modeling-based methods have recently shown significant performance across various downstream tasks. These pre-training…