Related papers: Metric Learning with Progressive Self-Distillation…
Speech representation learning approaches for non-semantic tasks such as language recognition have either explored supervised embedding extraction methods using a classifier model or self-supervised representation learning approaches using…
Voice interfaces integral to the human-computer interaction systems can benefit from speech emotion recognition (SER) to customize responses based on user emotions. Since humans convey emotions through multi-modal audio-visual cues,…
Practical autonomous driving systems face two crucial challenges: memory constraints and domain gap issues. In this paper, we present a novel approach to learn domain adaptive knowledge in models with limited memory, thus bestowing the…
Large-scale multi-view reconstruction models have made remarkable progress, but most existing approaches still rely on fully supervised training with ground-truth 3D/4D annotations. Such annotations are expensive and particularly scarce for…
Data-free knowledge distillation is a challenging model lightweight task for scenarios in which the original dataset is not available. Previous methods require a lot of extra computational costs to update one or more generators and their…
Knowledge distillation conducts an effective model compression method while holding some limitations:(1) the feature based distillation methods only focus on distilling the feature map but are lack of transferring the relation of data…
Purpose: In curriculum learning, the idea is to train on easier samples first and gradually increase the difficulty, while in self-paced learning, a pacing function defines the speed to adapt the training progress. While both methods…
Model compression and knowledge distillation have been successfully applied for cross-architecture and cross-domain transfer learning. However, a key requirement is that training examples are in correspondence across the domains. We show…
Cross-modal representation learning learns a shared embedding between two or more modalities to improve performance in a given task compared to using only one of the modalities. Cross-modal representation learning from different data types…
This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…
Representation learning has been proven to play an important role in the unprecedented success of machine learning models in numerous tasks, such as machine translation, face recognition and recommendation. The majority of existing…
As a prominent challenge in addressing real-world issues within a dynamic environment, label shift, which refers to the learning setting where the source (training) and target (testing) label distributions do not match, has recently…
Deep neural networks have proven to be highly effective when large amounts of data with clean labels are available. However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test…
Ensemble knowledge distillation can extract knowledge from multiple teacher models and encode it into a single student model. Many existing methods learn and distill the student model on labeled data only. However, the teacher models are…
We capitalize on large amounts of readily-available, synchronous data to learn a deep discriminative representations shared across three major natural modalities: vision, sound and language. By leveraging over a year of sound from video and…
Large-scale vision and language representation learning has shown promising improvements on various vision-language tasks. Most existing methods employ a transformer-based multimodal encoder to jointly model visual tokens (region-based…
In this work we propose a technique that transfers supervision between images from different modalities. We use learned representations from a large labeled modality as a supervisory signal for training representations for a new unlabeled…
Deep metric learning is often used to learn an embedding function that captures the semantic differences within a dataset. A key factor in many problem domains is how this embedding generalizes to new classes of data. In observing many…
Since deep learning became a key player in natural language processing (NLP), many deep learning models have been showing remarkable performances in a variety of NLP tasks, and in some cases, they are even outperforming humans. Such high…
Long-tailed multi-label visual recognition (LTML) task is a highly challenging task due to the label co-occurrence and imbalanced data distribution. In this work, we propose a unified framework for LTML, namely prompt tuning with…