相关论文: Class Based Thresholding in Early Exit Semantic Se…

Early-exit neural networks reduce inference cost by enabling confident predictions at intermediate layers. However, joint training often leads to gradient interference, with deeper classifiers dominating optimization. We propose…

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…

Prompt learning has emerged as an efficient alternative to fine-tuning pre-trained vision-language models (VLMs). Despite its promise, current methods still struggle to maintain tail-class discriminability when adapting to class-imbalanced…

This paper is aimed at developing a method that reduces the computational cost of convolutional neural networks (CNN) during inference. Conventionally, the input data pass through a fixed neural network architecture. However, easy examples…

Pre-trained Language Models (PLMs), like BERT, with self-supervision objectives exhibit remarkable performance and generalization across various tasks. However, they suffer in inference latency due to their large size. To address this…

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…

This paper addresses the task of semantic segmentation in computer vision, aiming to achieve precise pixel-wise classification. We investigate the joint training of models for semantic edge detection and semantic segmentation, which has…

Early-Exit Deep Neural Networks enable adaptive inference by allowing prediction at intermediary layers, significantly reducing computational costs and latency. Most of the early exit strategies greedily exit a sample at an intermediary…

The accelerating adoption of Large Language Models (LLMs) in software engineering (SE) has brought with it a silent crisis: unsustainable computational cost. While these models demonstrate remarkable capabilities in different SE tasks, they…

Early-exit neural networks enable adaptive inference by allowing predictions at intermediate layers, reducing computational cost. However, early exits often lack interpretability and may focus on different features than deeper layers,…

School dropout is a serious problem in distance learning, where early detection is crucial for effective intervention and student perseverance. Predicting student dropout using available educational data is a widely researched topic in…

This work invokes the notion of $f$-divergence to introduce a novel upper bound on the Bayes error rate of a general classification task. We show that the proposed bound can be computed by sampling from the output of a parameterized model.…

Semantic segmentation arises as the backbone of many vision systems, spanning from self-driving cars and robot navigation to augmented reality and teleconferencing. Frequently operating under stringent latency constraints within a limited…

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…

Vision-language models have showcased impressive zero-shot classification capabilities when equipped with suitable text prompts. Previous studies have shown the effectiveness of test-time prompt tuning; however, these methods typically…

Class incremental semantic segmentation aims to preserve old knowledge while learning new tasks, however, it is impeded by catastrophic forgetting and background shift issues. Prior works indicate the pivotal importance of initializing new…

Dynamic early exiting has been proven to improve the inference speed of the pre-trained language model like BERT. However, all samples must go through all consecutive layers before early exiting and more complex samples usually go through…

The Normalized Cut (NCut) objective function, widely used in data clustering and image segmentation, quantifies the cost of graph partitioning in a way that biases clusters or segments that are balanced towards having lower values than…

Early stopping techniques can be utilized to decrease the time cost, however currently the ultimate goal of early stopping techniques is closely related to the accuracy upgrade or the ability of the neural network to generalize better on…

Dynamic early exiting aims to accelerate the inference of pre-trained language models (PLMs) by emitting predictions in internal layers without passing through the entire model. In this paper, we empirically analyze the working mechanism of…