English
Related papers

Related papers: Index-Aligned Query Distillation for Transformer-b…

200 papers

In the era of large scale pretrained models, Knowledge Distillation (KD) serves an important role in transferring the wisdom of computationally heavy teacher models to lightweight, efficient student models while preserving performance.…

Machine Learning · Computer Science 2023-11-07 Alex Wilf , Alex Tianyi Xu , Paul Pu Liang , Alexander Obolenskiy , Daniel Fried , Louis-Philippe Morency

Knowledge distillation (KD) is widely used in audio tasks, such as speaker verification (SV), by transferring knowledge from a well-trained large model (the teacher) to a smaller, more compact model (the student) for efficiency and…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-17 Wenhao Yang , Jianguo Wei , Wenhuan Lu , Xugang Lu , Lei Li

Intelligent fault diagnosis has made extraordinary advancements currently. Nonetheless, few works tackle class-incremental learning for fault diagnosis under limited fault data, i.e., imbalanced and long-tailed fault diagnosis, which brings…

Machine Learning · Computer Science 2023-02-14 Peng Peng , Hanrong Zhang , Mengxuan Li , Gongzhuang Peng , Hongwei Wang , Weiming Shen

Incremental learning represents a crucial task in aerial image processing, especially given the limited availability of large-scale annotated datasets. A major issue concerning current deep neural architectures is known as catastrophic…

Computer Vision and Pattern Recognition · Computer Science 2021-12-08 Edoardo Arnaudo , Fabio Cermelli , Antonio Tavera , Claudio Rossi , Barbara Caputo

The widespread use of multi-sensor systems has increased research in multi-view action recognition. While existing approaches in multi-view setups with fully overlapping sensors benefit from consistent view coverage, partially overlapping…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Trung Thanh Nguyen , Yasutomo Kawanishi , Vijay John , Takahiro Komamizu , Ichiro Ide

Knowledge Distillation (KD) is one proposed solution to large model sizes and slow inference speed in semantic segmentation. In our research we identify 25 proposed distillation loss terms from 14 publications in the last 4 years.…

Computer Vision and Pattern Recognition · Computer Science 2023-09-08 Onno Niemann , Christopher Vox , Thorben Werner

Traditional knowledge distillation (KD) relies on a proficient teacher trained on the target task, which is not always available. In this setting, cross-task distillation can be used, enabling the use of any teacher model trained on a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-28 Dylan Auty , Roy Miles , Benedikt Kolbeinsson , Krystian Mikolajczyk

In this paper, we attempt to specialize the VLM model for OWOD tasks by distilling its open-world knowledge into a language-agnostic detector. Surprisingly, we observe that the combination of a simple \textbf{knowledge distillation}…

Computer Vision and Pattern Recognition · Computer Science 2024-04-02 Shuailei Ma , Yuefeng Wang , Ying Wei , Jiaqi Fan , Enming Zhang , Xinyu Sun , Peihao Chen

Most teacher-student frameworks based on knowledge distillation (KD) depend on a strong congruent constraint on instance level. However, they usually ignore the correlation between multiple instances, which is also valuable for knowledge…

Computer Vision and Pattern Recognition · Computer Science 2019-04-04 Baoyun Peng , Xiao Jin , Jiaheng Liu , Shunfeng Zhou , Yichao Wu , Yu Liu , Dongsheng Li , Zhaoning Zhang

Deep neural networks based methods have been proved to achieve outstanding performance on object detection and classification tasks. Despite significant performance improvement, due to the deep structures, they still require prohibitive…

Computer Vision and Pattern Recognition · Computer Science 2020-01-08 Mohammad Farhadi , Yezhou Yang

Event cameras are gaining popularity due to their unique properties, such as their low latency and high dynamic range. One task where these benefits can be crucial is real-time object detection. However, RGB detectors still outperform…

Computer Vision and Pattern Recognition · Computer Science 2023-11-10 Lei Li , Alexander Liniger , Mario Millhaeusler , Vagia Tsiminaki , Yuanyou Li , Dengxin Dai

Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Junhong Liu , Yuan Zhang , Tao Huang , Wenchao Xu , Renyu Yang

Surface defect detection is one of the most essential processes for industrial quality inspection. Deep learning-based surface defect detection methods have shown great potential. However, the well-performed models usually require large…

Computer Vision and Pattern Recognition · Computer Science 2022-09-02 Chen Sun , Liang Gao , Xinyu Li , Yiping Gao

Recent progresses on self-supervised 3D human action representation learning are largely attributed to contrastive learning. However, in conventional contrastive frameworks, the rich complementarity between different skeleton modalities…

Computer Vision and Pattern Recognition · Computer Science 2023-10-25 Yunyao Mao , Jiajun Deng , Wengang Zhou , Zhenbo Lu , Wanli Ouyang , Houqiang Li

Regarding intelligent transportation systems, low-bitrate transmission via lossy point cloud compression is vital for facilitating real-time collaborative perception among connected agents, such as vehicles and infrastructures, under…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Hao Jing , Anhong Wang , Yifan Zhang , Donghan Bu , Junhui Hou

Knowledge distillation is an effective technique for pre-trained language model compression. However, existing methods only focus on the knowledge distribution among layers, which may cause the loss of fine-grained information in the…

Computation and Language · Computer Science 2026-04-06 Zihe Liu , Yulong Mao , Jinan Xu , Xinrui Peng , Kaiyu Huang

Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models. However, existing works applying KD to QAT require tedious hyper-parameter tuning to…

Machine Learning · Computer Science 2024-03-19 Kaiqi Zhao , Ming Zhao

Knowledge distillation is an effective technique for pre-trained language model compression. Although existing knowledge distillation methods perform well for the most typical model BERT, they could be further improved in two aspects: the…

Computation and Language · Computer Science 2024-07-04 Ying Zhang , Ziheng Yang , Shufan Ji

Despite that current reading comprehension systems have achieved significant advancements, their promising performances are often obtained at the cost of making an ensemble of numerous models. Besides, existing approaches are also…

Computation and Language · Computer Science 2018-09-18 Minghao Hu , Yuxing Peng , Furu Wei , Zhen Huang , Dongsheng Li , Nan Yang , Ming Zhou

Continual learning refers to a dynamical framework in which a model receives a stream of non-stationary data over time and must adapt to new data while preserving previously acquired knowledge. Unluckily, neural networks fail to meet these…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-24 Umberto Cappellazzo , Daniele Falavigna , Alessio Brutti