Dynamic neural networks: A survey

Y Han, G Huang, S Song, L Yang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
Dynamic neural network is an emerging research topic in deep learning. Compared to static
models which have fixed computational graphs and parameters at the inference stage …

IA-RED: Interpretability-Aware Redundancy Reduction for Vision Transformers

B Pan, R Panda, Y Jiang, Z Wang… - Advances in Neural …, 2021 - proceedings.neurips.cc
The self-attention-based model, transformer, is recently becoming the leading backbone in
the field of computer vision. In spite of the impressive success made by transformers in a …

Dynamic perceiver for efficient visual recognition

Y Han, D Han, Z Liu, Y Wang, X Pan… - Proceedings of the …, 2023 - openaccess.thecvf.com
Early exiting has become a promising approach to im-proving the inference efficiency of
deep networks. By structuring models with multiple classifiers (exits), predictions for" easy" …

Adaptive focus for efficient video recognition

Y Wang, Z Chen, H Jiang, S Song… - proceedings of the …, 2021 - openaccess.thecvf.com
In this paper, we explore the spatial redundancy in video recognition with the aim to improve
the computational efficiency. It is observed that the most informative region in each frame of …

Frameexit: Conditional early exiting for efficient video recognition

A Ghodrati, BE Bejnordi… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
In this paper, we propose a conditional early exiting framework for efficient video
recognition. While existing works focus on selecting a subset of salient frames to reduce the …

Adapting Neural Networks at Runtime: Current Trends in At-Runtime Optimizations for Deep Learning

M Sponner, B Waschneck, A Kumar - ACM Computing Surveys, 2024 - dl.acm.org
Adaptive optimization methods for deep learning adjust the inference task to the current
circumstances at runtime to improve the resource footprint while maintaining the model's …

Motion stimulation for compositional action recognition

L Ma, Y Zheng, Z Zhang, Y Yao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Recognizing the unseen combinations of action and different objects, namely (zero-shot)
compositional action recognition, is extremely challenging for conventional action …

Adafocus v2: End-to-end training of spatial dynamic networks for video recognition

Y Wang, Y Yue, Y Lin, H Jiang, Z Lai… - 2022 IEEE/CVF …, 2022 - ieeexplore.ieee.org
Recent works have shown that the computational efficiency of video recognition can be
significantly improved by reducing the spatial redundancy. As a representative work, the …

Dynamic network quantization for efficient video inference

X Sun, R Panda, CFR Chen, A Oliva… - Proceedings of the …, 2021 - openaccess.thecvf.com
Deep convolutional networks have recently achieved great success in video recognition, yet
their practical realization remains a challenge due to the large amount of computational …

Adamml: Adaptive multi-modal learning for efficient video recognition

R Panda, CFR Chen, Q Fan, X Sun… - Proceedings of the …, 2021 - openaccess.thecvf.com
Multi-modal learning, which focuses on utilizing various modalities to improve the
performance of a model, is widely used in video recognition. While traditional multi-modal …