English
Related papers

Related papers: Multi-Head Explainer: A General Framework to Impro…

200 papers

Deep convolutional neural networks have revolutionized many machine learning and computer vision tasks, however, some remaining key challenges limit their wider use. These challenges include improving the network's robustness to…

Computer Vision and Pattern Recognition · Computer Science 2019-05-21 Eldad Haber , Keegan Lensink , Eran Treister , Lars Ruthotto

This paper introduces innovative frameworks for visual abstract reasoning, aiming to boost deep learning model performance. It emphasizes the importance of separating abstract concept and reasoning feature extraction processes. The…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Ruizhuo Song , Beiming Yuan

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and…

Computation and Language · Computer Science 2020-01-06 Goran Glavaš , Swapna Somasundaran

Despite the success of convolution- and attention-based models in vision tasks, their rigid receptive fields and complex architectures limit their ability to model irregular spatial patterns and hinder interpretability, therefore posing…

Computer Vision and Pattern Recognition · Computer Science 2025-12-22 Xiangshuai Song , Jun-Jie Huang , Tianrui Liu , Ke Liang , Chang Tang

Salient object detection requires a comprehensive and scalable receptive field to locate the visually significant objects in the image. Recently, the emergence of visual transformers and multi-branch modules has significantly enhanced the…

Computer Vision and Pattern Recognition · Computer Science 2021-10-18 Mingcan Ma , Changqun Xia , Chenxi Xie , Xiaowu Chen , Jia Li

Multiscale feature hierarchies have been witnessed the success in the computer vision area. This further motivates researchers to design multiscale Transformer for natural language processing, mostly based on the self-attention mechanism.…

Computation and Language · Computer Science 2022-06-22 Bei Li , Tong Zheng , Yi Jing , Chengbo Jiao , Tong Xiao , Jingbo Zhu

Since the introduction of the Transformer architecture for large language models, the softmax-based attention layer has faced increasing scrutinity due to its quadratic-time computational complexity. Attempts have been made to replace it…

Machine Learning · Computer Science 2026-02-02 Robert Forchheimer

Multimodal Sentiment Analysis (MSA) with missing modalities has recently attracted increasing attention. Although existing research mainly focuses on designing complex model architectures to handle incomplete data, it still faces…

Multimedia · Computer Science 2025-08-01 Xiang Li , Xianfu Cheng , Xiaoming Zhang , Zhoujun Li

In this paper, we propose a novel architecture for multi-modal speech and text input. We combine pretrained speech and text encoders using multi-headed cross-modal attention and jointly fine-tune on the target problem. The resultant…

Computation and Language · Computer Science 2022-04-21 Karan Singla , Daniel Pressel , Ryan Price , Bhargav Srinivas Chinnari , Yeon-Jun Kim , Srinivas Bangalore

State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are…

Computation and Language · Computer Science 2023-05-30 Florian Mai , Juan Zuluaga-Gomez , Titouan Parcollet , Petr Motlicek

Transformer models achieve state-of-the-art performance across domains and tasks, yet their deeply layered representations make their predictions difficult to interpret. Existing explainability methods rely on final-layer attributions,…

Computation and Language · Computer Science 2026-05-21 Melkamu Abay Mersha , Jugal Kalita

Convolutional neural networks (CNNs) offer great machine learning performance over a range of applications, but their operation is hard to interpret, even for experts. Various explanation algorithms have been proposed to address this issue,…

Human-Computer Interaction · Computer Science 2020-02-04 Ahmed Alqaraawi , Martin Schuessler , Philipp Weiß , Enrico Costanza , Nadia Berthouze

Deep learning and Convolutional Neural Networks (CNNs) have driven major transformations in diverse research areas. However, their limitations in handling low-frequency information present obstacles in certain tasks like interpreting global…

Computer Vision and Pattern Recognition · Computer Science 2024-03-14 Fuzhi Wu , Jiasong Wu , Youyong Kong , Chunfeng Yang , Guanyu Yang , Huazhong Shu , Guy Carrault , Lotfi Senhadji

Vision Transformer and its variants have demonstrated great potential in various computer vision tasks. But conventional vision transformers often focus on global dependency at a coarse level, which suffer from a learning challenge on…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Yunhao Wang , Huixin Sun , Xiaodi Wang , Bin Zhang , Chao Li , Ying Xin , Baochang Zhang , Errui Ding , Shumin Han

Transformers are widely used in natural language processing, where they consistently achieve state-of-the-art performance. This is mainly due to their attention-based architecture, which allows them to model rich linguistic relations…

Computation and Language · Computer Science 2022-11-29 Nikolaos Mylonas , Ioannis Mollas , Grigorios Tsoumakas

Transformer layers, which use an alternating pattern of multi-head attention and multi-layer perceptron (MLP) layers, provide an effective tool for a variety of machine learning problems. As the transformer layers use residual connections…

Machine Learning · Computer Science 2022-12-13 Yaofeng Desmond Zhong , Tongtao Zhang , Amit Chakraborty , Biswadip Dey

There has been profound progress in visual saliency thanks to the deep learning architectures, however, there still exist three major challenges that hinder the detection performance for scenes with complex compositions, multiple salient…

Computer Vision and Pattern Recognition · Computer Science 2017-08-16 Jing Zhang , Yuchao Dai , Fatih Porikli , Mingyi He

Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Shi Chen , Qi Zhao

The long-context capability of recent large transformer models can be surmised to rely on techniques such as attention/model parallelism, as well as hardware-level optimizations. While these strategies allow input lengths to scale to…

Computer Vision and Pattern Recognition · Computer Science 2025-07-28 Toufiq Parag , Ahmed Elgammal

Deep convolutional networks have been quite successful at various image classification tasks. The current methods to explain the predictions of a pre-trained model rely on gradient information, often resulting in saliency maps that focus on…

Machine Learning · Computer Science 2020-11-04 Ashish Kumar , Karan Sehgal , Prerna Garg , Vidhya Kamakshi , Narayanan C Krishnan