相关论文: FrameExit: Conditional Early Exiting for Efficient…

As a simple technique to accelerate inference of large-scale pre-trained models, early exiting has gained much attention in the NLP community. It allows samples to exit early at internal classifiers without passing through the entire model.…

By adding exiting layers to the deep learning networks, early exit can terminate the inference earlier with accurate results. The passive decision-making of whether to exit or continue the next layer has to go through every pre-placed…

Despite recent interest and advances in facial micro-expression research, there is still plenty room for improvement in terms of micro-expression recognition. Conventional feature extraction approaches for micro-expression video consider…

Robust scene segmentation and keyframe extraction are essential preprocessing steps in video understanding pipelines, supporting tasks such as indexing, summarization, and semantic retrieval. However, existing methods often lack…

Vision transformers have recently made a breakthrough in computer vision showing excellent performance in terms of precision for numerous applications. However, their computational cost is very high compared to alternative approaches such…

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 a video is usually a small image patch, which…

By leveraging the data sample diversity, the early-exit network recently emerges as a prominent neural network architecture to accelerate the deep learning inference process. However, intermediate classifiers of the early exits introduce…

Early exiting is an effective paradigm for improving the inference efficiency of deep networks. By constructing classifiers with varying resource demands (the exits), such networks allow easy samples to be output at early exits, removing…

Deploying large language model inference remains challenging due to their high computational overhead. Early exit optimizes model inference by adaptively reducing the number of inference layers. Current methods typically train internal…

Multi-step prediction models, such as diffusion and rectified flow models, have emerged as state-of-the-art solutions for generation tasks. However, these models exhibit higher latency in sampling new frames compared to single-step methods.…

Detection-driven real-time video analytics require continuous detection of objects contained in the video frames using deep learning models like YOLOV3, EfficientDet. However, running these detectors on each and every frame in…

We present AdaFrame, a framework that adaptively selects relevant frames on a per-input basis for fast video recognition. AdaFrame contains a Long Short-Term Memory network augmented with a global memory that provides context information…

Building efficient inference framework has gained increasing interests for research community. Early-exit models, a variant of LLMs, improves the inference efficiency of LLMs by skipping rest layers and directly generate output tokens when…

Both performance and efficiency are crucial factors for sequence labeling tasks in many real-world scenarios. Although the pre-trained models (PTMs) have significantly improved the performance of various sequence labeling tasks, their…

Typical video classification methods often divide a video into short clips, do inference on each clip independently, then aggregate the clip-level predictions to generate the video-level results. However, processing visually similar clips…

Recently, 3D convolutional networks yield good performance in action recognition. However, optical flow stream is still needed to ensure better performance, the cost of which is very high. In this paper, we propose a fast but effective way…

State-of-the-art neural networks with early exit mechanisms often need considerable amount of training and fine tuning to achieve good performance with low computational cost. We propose a novel early exit technique, Early Exit Class Means…

Despite much success in natural language processing (NLP), pre-trained language models typically lead to a high computational cost during inference. Multi-exit is a mainstream approach to address this issue by making a trade-off between…

Early exiting has become a promising approach to improving the inference efficiency of deep networks. By structuring models with multiple classifiers (exits), predictions for ``easy'' samples can be generated at earlier exits, negating the…

Early exiting allows instances to exit at different layers according to the estimation of difficulty. Previous works usually adopt heuristic metrics such as the entropy of internal outputs to measure instance difficulty, which suffers from…