Related papers: Global-Local Distillation Network-Based Audio-Visu…

Large-scale language models have recently demonstrated impressive empirical performance. Nevertheless, the improved results are attained at the price of bigger models, more power consumption, and slower inference, which hinder their…

Previous works have attempted to improve tracking efficiency through lightweight architecture design or knowledge distillation from teacher models to compact student trackers. However, these solutions often sacrifice accuracy for speed to a…

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,…

While large audio language models excel at tasks like ASR and emotion recognition, they still struggle with complex reasoning due to the modality gap between audio and text as well as the lack of structured intermediate supervision. To…

Discrete diffusion models (DDMs) have shown powerful generation ability for discrete data modalities like text and molecules. However, their practical application is hindered by inefficient sampling, requiring a large number of sampling…

We study timestamped speaker-attributed ASR for long-form, multi-party speech with overlap, where chunk-wise inference must preserve meeting-level speaker identity consistency while producing time-stamped, speaker-labeled transcripts.…

In this work, we present a novel method, named AV2vec, for learning audio-visual speech representations by multimodal self-distillation. AV2vec has a student and a teacher module, in which the student performs a masked latent feature…

Infrared and visible image fusion plays a critical role in enhancing scene perception by combining complementary information from different modalities. Despite recent advances, achieving high-quality image fusion with lightweight models…

Training speaker-discriminative and robust speaker verification systems without explicit speaker labels remains a persisting challenge. In this paper, we propose a new self-supervised speaker verification approach, Self-Distillation…

Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always…

Edge devices operate in constrained and varying resource settings, requiring dynamic architectures that can adapt to limitations of the available resources. To meet such demands, layer dropping ($\mathcal{LD}$) approach is typically used to…

The smaller memory bandwidth in smart devices prompts development of smaller Automatic Speech Recognition (ASR) models. To obtain a smaller model, one can employ the model compression techniques. Knowledge distillation (KD) is a popular…

With the increasing adoption of video anomaly detection in intelligent surveillance domains, conventional visual-based detection approaches often struggle with information insufficiency and high false-positive rates in complex environments.…

In single-channel speech enhancement, methods based on full-band spectral features have been widely studied. However, only a few methods pay attention to non-full-band spectral features. In this paper, we explore a knowledge distillation…

Knowledge distillation (KD) is widely used for compressing a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, current KD methods for auto-regressive sequence models suffer from…

Vision-Language Tracking aims to continuously localize objects described by a visual template and a language description. Existing methods, however, are typically limited to local search, making them prone to failures under viewpoint…

Knowledge Distillation (KD) is a promising approach for unsupervised Anomaly Detection (AD). However, the student network's over-generalization often diminishes the crucial representation differences between teacher and student in anomalous…

Monocular 3D object detection is a promising yet ill-posed task for autonomous vehicles due to the lack of accurate depth information. Cross-modality knowledge distillation could effectively transfer depth information from LiDAR to…

In this paper, we introduce a novel knowledge distillation approach for the semantic segmentation task. Unlike previous methods that rely on power-trained teachers or other modalities to provide additional knowledge, our approach does not…

Open-vocabulary 3D instance segmentation seeks to segment and classify instances beyond the annotated label space. Existing methods typically map 3D instances to 2D RGB-D images, and then employ vision-language models (VLMs) for…