Related papers: VT-Former: Efffcient Transformer-based Decoder for…

Interactive speech recognition systems must generate words quickly while also producing accurate results. Two-pass models excel at these requirements by employing a first-pass decoder that quickly emits words, and a second-pass decoder that…

At the core of the Transformer, the softmax normalizes the attention matrix to be right stochastic. Previous research has shown that this often de-stabilizes training and that enforcing the attention matrix to be doubly stochastic (through…

Change detection (CD) in remote sensing aims to identify semantic differences between satellite images captured at different times. While deep learning has significantly advanced this field, existing approaches based on convolutional neural…

Recent Large View Synthesis Models (LVSMs) advocate an encoder-decoder architecture that separates reconstruction and rendering into distinct networks. We re-examine this design. Through controlled experiments, we show that a decoder-only…

In recent years, deep neural networks (DNNs) trained with transformed data have been applied to various applications such as privacy-preserving learning, access control, and adversarial defenses. However, the use of transformed data…

Transformers are very powerful tools for a variety of tasks across domains, from text generation to image captioning. However, transformers require substantial amounts of training data, which is often a challenge in biomedical settings,…

Image Representation learning via input reconstruction is a common technique in machine learning for generating representations that can be effectively utilized by arbitrary downstream tasks. A well-established approach is using…

Deep neural networks are vulnerable to input deformations in the form of vector fields of pixel displacements and to other parameterized geometric deformations e.g. translations, rotations, etc. Current input deformation certification…

We investigate the problem of multi-domain Dialogue State Tracking (DST) with open vocabulary. Existing approaches exploit BERT encoder and copy-based RNN decoder, where the encoder predicts the state operation, and the decoder generates…

Transformer-based language models are highly effective for code completion, with much research dedicated to enhancing the content of these completions. Despite their effectiveness, these models come with high operational costs and can be…

This work develops problem statements related to encoders and autoencoders with the goal of elucidating variational formulations and establishing clear connections to information-theoretic concepts. Specifically, four problems with varying…

This work aims to tackle the all-in-one image restoration task, which seeks to handle multiple types of degradation with a single model. The primary challenge is to extract degradation representations from the input degraded images and use…

Tables organize valuable content in a concise and compact representation. This content is extremely valuable for systems such as search engines, Knowledge Graph's, etc, since they enhance their predictive capabilities. Unfortunately, tables…

Real-world weather, illumination, and imaging variations often induce severe domain shifts, degrading single-source detectors in unseen environments. Existing single-domain generalized object detection (SDGOD) methods mainly rely on data…

Transformer has achieved great success in computer vision, while how to split patches in an image remains a problem. Existing methods usually use a fixed-size patch embedding which might destroy the semantics of objects. To address this…

Recent TTS models with decoder-only Transformer architecture, such as SPEAR-TTS and VALL-E, achieve impressive naturalness and demonstrate the ability for zero-shot adaptation given a speech prompt. However, such decoder-only TTS models…

The recent trend in multiple object tracking (MOT) is heading towards leveraging deep learning to boost the tracking performance. In this paper, we propose a novel solution named TransSTAM, which leverages Transformer to effectively model…

Recently, deep learning methods have achieved state-of-the-art performance in many medical image segmentation tasks. Many of these are based on convolutional neural networks (CNNs). For such methods, the encoder is the key part for global…

Accurate vessel trajectory prediction is necessary for save and efficient navigation. Deep learning-based prediction models, esp. encoder-decoders, are rarely applied to inland navigation specifically. Approaches from the maritime domain…

Transformer-based QA models use input-wide self-attention -- i.e. across both the question and the input passage -- at all layers, causing them to be slow and memory-intensive. It turns out that we can get by without input-wide…