Related papers: Applying SoftTriple Loss for Supervised Language M…
Few-shot learning aims to generalize unseen classes that appear during testing but are unavailable during training. Prototypical networks incorporate few-shot metric learning, by constructing a class prototype in the form of a mean vector…
Data augmentation has shown its effectiveness in resolving the data-hungry problem and improving model's generalization ability. However, the quality of augmented data can be varied, especially compared with the raw/original data. To boost…
We propose adaptive weight decay, which automatically tunes the hyper-parameter for weight decay during each training iteration. For classification problems, we propose changing the value of the weight decay hyper-parameter on the fly based…
In deep learning classifiers, the cost function usually takes the form of a combination of SoftMax and CrossEntropy functions. The SoftMax unit transforms the scores predicted by the model network into assessments of the degree…
In recent years, the softmax model and its fast approximations have become the de-facto loss functions for deep neural networks when dealing with multi-class prediction. This loss has been extended to language modeling and recommendation,…
Foundation language models learn from their finetuning input context in different ways. In this paper, we reformulate inputs during finetuning for challenging translation tasks, leveraging model strengths from pretraining in novel ways to…
Adapting deep learning models to new domains often requires computationally intensive retraining and risks catastrophic forgetting. While fine-tuning enables domain-specific adaptation, it can reduce robustness to distribution shifts,…
We address the problem of distance metric learning in visual similarity search, defined as learning an image embedding model which projects images into Euclidean space where semantically and visually similar images are closer and dissimilar…
Recent studies have shown that deep neural networks are not well-calibrated and often produce over-confident predictions. The miscalibration issue primarily stems from using cross-entropy in classifications, which aims to align predicted…
Reinforcement Learning (RL) is a powerful framework to address the discrepancy between loss functions used during training and the final evaluation metrics to be used at test time. When applied to neural Machine Translation (MT), it…
Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current robust loss functions, however, inevitably involve hyperparameter(s) to be tuned, manually or heuristically through cross…
Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial examples. In this paper, we improve the robustness of DNNs by utilizing techniques of Distance Metric Learning. Specifically, we incorporate…
Multilingual pretraining for transfer learning significantly boosts the robustness of low-resource monolingual ASR models. This study systematically investigates three main aspects: (a) the impact of transfer learning on model performance…
We develop a higher-order asymptotic analysis for the semi-hard triplet loss using the Edgeworth expansion. It is known that this loss function enforces that embeddings of similar samples are close while those of dissimilar samples are…
As access to high-quality, domain-specific data grows increasingly scarce, multi-epoch training has become a practical strategy for adapting large language models (LLMs). However, autoregressive models often suffer from performance…
In the domain of Natural Language Inference (NLI), especially in tasks involving the classification of multiple input texts, the Cross-Entropy Loss metric is widely employed as a standard for error measurement. However, this metric falls…
This work presents a study on label noise in medical image segmentation by considering a noise model based on Gaussian field deformations. Such noise is of interest because it yields realistic looking segmentations and because it is…
Self-supervised monocular depth estimation (MDE) models universally suffer from the notorious edge-fattening issue. Triplet loss, as a widespread metric learning strategy, has largely succeeded in many computer vision applications. In this…
Sequence-to-Sequence (Seq2Seq) models have achieved encouraging performance on the dialogue response generation task. However, existing Seq2Seq-based response generation methods suffer from a low-diversity problem: they frequently generate…
Nowadays, deep learning is the standard approach for a wide range of problems, including biometrics, such as face recognition and speech recognition, etc. Biometric problems often use deep learning models to extract features from images,…