Related papers: Beyond Prototypes: Semantic Anchor Regularization …

Meta-learning aims to learn general knowledge with diverse training tasks conducted from limited data, and then transfer it to new tasks. It is commonly believed that increasing task diversity will enhance the generalization ability of…

Self-supervised Learning (SSL) aims to learn transferable feature representations for downstream applications without relying on labeled data. The Barlow Twins algorithm, renowned for its widespread adoption and straightforward…

In several applications, input samples are more naturally represented in terms of similarities between each other, rather than in terms of feature vectors. In these settings, machine-learning algorithms can become very computationally…

Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning because they are able to extract high-quality salient features from input data. As such, they have…

Standard fine-tuning of pre-trained audio models couples representation learning with classifier training, which can obscure the true quality of the learned representations. In this work, we advocate for a disentangled two-stage framework…

For many practical computer vision applications, the learned models usually have high performance on the datasets used for training but suffer from significant performance degradation when deployed in new environments, where there are…

Recently self-supervised representation learning has drawn considerable attention from the scene text recognition community. Different from previous studies using contrastive learning, we tackle the issue from an alternative perspective,…

We propose a new convolutional neural network (CNN) which performs coarse and fine segmentation for end-to-end synthetic aperture radar (SAR) automatic target recognition (ATR) system. In recent years, many CNNs for SAR ATR using deep…

Aiming to incrementally learn new classes with only few samples while preserving the knowledge of base (old) classes, few-shot class-incremental learning (FSCIL) faces several challenges, such as overfitting and catastrophic forgetting.…

A recent study has shown a phenomenon called neural collapse in that the within-class means of features and the classifier weight vectors converge to the vertices of a simplex equiangular tight frame at the terminal phase of training for…

This paper presents a new supervised representation learning framework, namely structured probabilistic coding (SPC), to learn compact and informative representations from input related to the target task. SPC is an encoder-only…

End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the…

In zero-shot learning (ZSL), generative methods synthesize class-related sample features based on predefined semantic prototypes. They advance the ZSL performance by synthesizing unseen class sample features for better training the…

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…

Continual learning aims to enable models to acquire new knowledge while retaining previously learned information. Prompt-based methods have shown remarkable performance in this domain; however, they typically rely on key-value pairing,…

Abstract Meaning Representations (AMR) are a broad-coverage semantic formalism which represents sentence meaning as a directed acyclic graph. To train most AMR parsers, one needs to segment the graph into subgraphs and align each such…

There have been significant advancements in anomaly detection in an unsupervised manner, where only normal images are available for training. Several recent methods aim to detect anomalies based on a memory, comparing or reconstructing the…

Implicit representation of an image can map arbitrary coordinates in the continuous domain to their corresponding color values, presenting a powerful capability for image reconstruction. Nevertheless, existing implicit representation…

Federated learning is widely used to perform decentralized training of a global model on multiple devices while preserving the data privacy of each device. However, it suffers from heterogeneous local data on each training device which…

In view of the fact that semi- and self-supervised learning share a fundamental principle, effectively modeling knowledge from unlabeled data, various semi-supervised semantic segmentation methods have integrated representative…