相关论文: Training with Streaming Annotation

Deep learning based visual trackers entail offline pre-training on large volumes of video datasets with accurate bounding box annotations that are labor-expensive to achieve. We present a new framework to facilitate bounding box annotations…

Transfer learning for bio-signals has recently become an important technique to improve prediction performance on downstream tasks with small bio-signal datasets. Recent works have shown that pre-training a neural network model on a large…

Overparameterization has been shown to benefit both the optimization and generalization of neural networks, but large networks are resource hungry at both training and test time. Network pruning can reduce test-time resource requirements,…

Transferring knowledge from one neural network to another has been shown to be helpful for learning tasks with few training examples. Prevailing fine-tuning methods could potentially contaminate pre-trained features by comparably high…

Recently self-supervised learning has emerged as an effective approach to improve the performance of automatic speech recognition (ASR). Under such a framework, the neural network is usually pre-trained with massive unlabeled data and then…

Auto-annotation by ensemble of models is an efficient method of learning on unlabeled data. Wrong or inaccurate annotations generated by the ensemble may lead to performance degradation of the trained model. To deal with this problem we…

This work presents the first condensation approach for procedural video datasets used in temporal action segmentation. We propose a condensation framework that leverages generative prior learned from the dataset and network inversion to…

Post-training (via supervised fine-tuning) improves instruction-following, but often induces semantic mode collapse by biasing models toward low-entropy fine-tuning data at the expense of the high-entropy pretraining distribution.…

Neural models for abstractive summarization tend to achieve the best performance in the presence of highly specialized, summarization specific modeling add-ons such as pointer-generator, coverage-modeling, and inferencetime heuristics. We…

Pre-trained language model representations have been successful in a wide range of language understanding tasks. In this paper, we examine different strategies to integrate pre-trained representations into sequence to sequence models and…

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of…

High-quality computer science education is limited by the difficulty of providing instructor feedback to students at scale. While this feedback could in principle be automated, supervised approaches to predicting the correct feedback are…

We explore training attention-based encoder-decoder ASR in low-resource settings. These models perform poorly when trained on small amounts of transcribed speech, in part because they depend on having sufficient target-side text to train…

Deep pretrained transformer networks are effective at various ranking tasks, such as question answering and ad-hoc document ranking. However, their computational expenses deem them cost-prohibitive in practice. Our proposed approach, called…

Despite being the current de-facto models in most NLP tasks, transformers are often limited to short sequences due to their quadratic attention complexity on the number of tokens. Several attempts to address this issue were studied, either…

In anticipatory networking, channel prediction is used to improve communication performance. This paper describes a new approach for allocating resources to video streaming traffic while accounting for quality of service. The proposed…

Comprehensive surgical planning require complex patient-specific anatomical models. For instance, functional muskuloskeletal simulations necessitate all relevant structures to be segmented, which could be performed in real-time using deep…

Annotated datasets are an essential ingredient to train, evaluate, compare and productionalize supervised machine learning models. It is therefore imperative that annotations are of high quality. For their creation, good quality management…

In streaming Reinforcement Learning (RL), transitions are observed and discarded immediately after a single update. While this minimizes resource usage for on-device applications, it makes agents notoriously sample-inefficient, since…

Existing trajectory prediction methods exhibit significant performance degradation under distribution shifts during test time. Although test-time training techniques have been explored to enable adaptation, current approaches rely on an…