Related papers: Transformer Interpretability Beyond Attention Visu…

Mathematical reasoning is one of the most impressive achievements of human intellect but remains a formidable challenge for artificial intelligence systems. In this work we explore whether modern deep learning architectures can learn to…

Deployments of artificial intelligence in medical diagnostics mandate not just accuracy and efficacy but also trust, emphasizing the need for explainability in machine decisions. The recent trend in automated medical image diagnostics leans…

We propose a novel attention model that can accurately attends to target objects of various scales and shapes in images. The model is trained to gradually suppress irrelevant regions in an input image via a progressive attentive process…

Recently, learned image compression methods have outperformed traditional hand-crafted ones including BPG. One of the keys to this success is learned entropy models that estimate the probability distribution of the quantized latent…

This paper targets two transformer attention based interpretability methods working with local abstraction and global representation, in the context of time series data. We distinguish local and global contexts, and provide a comprehensive…

Deep neural networks (DNNs) have demonstrated remarkable success, yet their wide adoption is often hindered by their opaque decision-making. To address this, attribution methods have been proposed to assign relevance values to each part of…

Due to the highly parallelizable architecture, Transformer is faster to train than RNN-based models and popularly used in machine translation tasks. However, at inference time, each output word requires all the hidden states of the…

Vision Transformers (ViTs) have achieved state-of-the-art performance in image classification, yet their attention mechanisms often remain opaque and exhibit dense, non-structured behaviors. In this work, we adapt our previously proposed…

The interest in complex deep neural networks for computer vision applications is increasing. This leads to the need for improving the interpretable capabilities of these models. Recent explanation methods present visualizations of the…

In both Computer Vision and the wider Deep Learning field, the Transformer architecture is well-established as state-of-the-art for many applications. For Multitask Learning, however, where there may be many more queries necessary compared…

A dramatic rise in the flow of manipulated image content on the Internet has led to an aggressive response from the media forensics research community. New efforts have incorporated increased usage of techniques from computer vision and…

Attention mechanism has been used as an ancillary means to help RNN or CNN. However, the Transformer (Vaswani et al., 2017) recently recorded the state-of-the-art performance in machine translation with a dramatic reduction in training time…

Scene text recognition with arbitrary shape is very challenging due to large variations in text shapes, fonts, colors, backgrounds, etc. Most state-of-the-art algorithms rectify the input image into the normalized image, then treat the…

The fully convolutional network (FCN) has dominated salient object detection for a long period. However, the locality of CNN requires the model deep enough to have a global receptive field and such a deep model always leads to the loss of…

The Transformer translation model is based on the multi-head attention mechanism, which can be parallelized easily. The multi-head attention network performs the scaled dot-product attention function in parallel, empowering the model by…

Transformers flexibly operate over sets of real-valued vectors representing task-specific entities and their attributes, where each vector might encode one word-piece token and its position in a sequence, or some piece of information that…

Visual transformers have achieved remarkable performance in image classification tasks, but this performance gain has come at the cost of interpretability. One of the main obstacles to the interpretation of transformers is the…

Recent progress on parse tree encoder for sentence representation learning is notable. However, these works mainly encode tree structures recursively, which is not conducive to parallelization. On the other hand, these works rarely take…

The field of image classification has shown an outstanding success thanks to the development of deep learning techniques. Despite the great performance obtained, most of the work has focused on natural images ignoring other domains like…

Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…