Related papers: Perception and Semantic Aware Regularization for S…

Deep neural networks have been shown to be highly miscalibrated. often they tend to be overconfident in their predictions. It poses a significant challenge for safety-critical systems to utilise deep neural networks (DNNs), reliably. Many…

In order to develop effective sequential recommenders, a series of sequence representation learning (SRL) methods are proposed to model historical user behaviors. Most existing SRL methods rely on explicit item IDs for developing the…

Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the tokenizer vocabulary. In this work, we investigate the…

Consistency regularization on label predictions becomes a fundamental technique in semi-supervised learning, but it still requires a large number of training iterations for high performance. In this study, we analyze that the consistency…

Scene labeling is a challenging classification problem where each input image requires a pixel-level prediction map. Recently, deep-learning-based methods have shown their effectiveness on solving this problem. However, we argue that the…

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

In the domain of moment retrieval, accurately identifying temporal segments within videos based on natural language queries remains challenging. Traditional methods often employ pre-trained models that struggle with fine-grained information…

Understanding deep neural network (DNN) behavior requires more than evaluating classification accuracy alone; analyzing errors and their predictability is equally crucial. Current evaluation methodologies lack transparency, particularly in…

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem,…

In this work, we introduce a simple yet efficient post-processing model for automatic speech recognition (ASR). Our model has Transformer-based encoder-decoder architecture which "translates" ASR model output into grammatically and…

This paper is about regularizing deep convolutional networks (CNNs) based on an adaptive framework for transfer learning with limited training data in the target domain. Recent advances of CNN regularization in this context are commonly due…

Few-shot image classification requires the classifier to robustly cope with unseen classes even if there are only a few samples for each class. Recent advances benefit from the meta-learning process where episodic tasks are formed to train…

Modern language models (LMs) are trained in an autoregressive manner, conditioned only on the prefix. In contrast, sequence labeling (SL) tasks assign labels to each individual input token, naturally benefiting from bidirectional context.…

Deep neural networks (DNNs) excel on fixed datasets but struggle with incremental and shifting data in real-world scenarios. Continual learning addresses this challenge by allowing models to learn from new data while retaining previously…

We propose a novel multi-task pre-training method for Speech Emotion Recognition (SER). We pre-train SER model simultaneously on Automatic Speech Recognition (ASR) and sentiment classification tasks to make the acoustic ASR model more…

Deep models trained on source domain lack generalization when evaluated on unseen target domains with different data distributions. The problem becomes even more pronounced when we have no access to target domain samples for adaptation. In…

Recent advances in deep learning significantly boost the performance of salient object detection (SOD) at the expense of labeling larger-scale per-pixel annotations. To relieve the burden of labor-intensive labeling, deep unsupervised SOD…

Recent explainability related studies have shown that state-of-the-art DNNs do not always adopt correct evidences to make decisions. It not only hampers their generalization but also makes them less likely to be trusted by end-users. In…

While recent studies on semi-supervised learning have shown remarkable progress in leveraging both labeled and unlabeled data, most of them presume a basic setting of the model is randomly initialized. In this work, we consider…

The lack of out-of-domain generalization is a critical weakness of deep networks for semantic segmentation. Previous studies relied on the assumption of a static model, i. e., once the training process is complete, model parameters remain…