Related papers: Feature Distribution Shift Mitigation with Contras…

Representation learning has been evolving from traditional supervised training to Contrastive Learning (CL) and Masked Image Modeling (MIM). Previous works have demonstrated their pros and cons in specific scenarios, i.e., CL and supervised…

The primary goal of training in early convolutional neural networks (CNN) is the higher generalization performance of the model. However, as the expected calibration error (ECE), which quantifies the explanatory power of model inference,…

Though deep neural networks have achieved impressive success on various vision tasks, obvious performance degradation still exists when models are tested in out-of-distribution scenarios. In addressing this limitation, we ponder that the…

Navigation Foundation Models (NFMs) trained on large cross-embodied datasets have demonstrated powerful generalizability in various scenarios. Adopting in-domain fine-tuning for an NFM efficiently calibrates the visuomotor policy, promising…

Model compression has emerged as an important area of research for deploying deep learning models on Internet-of-Things (IoT). However, for extremely memory-constrained scenarios, even the compressed models cannot fit within the memory of a…

The increasing global prevalence of mental disorders, such as depression and PTSD, requires objective and scalable diagnostic tools. Traditional clinical assessments often face limitations in accessibility, objectivity, and consistency.…

Non-negative Matrix Factorization (NMF) has proven to be a powerful unsupervised learning method for uncovering hidden features in complex and noisy data sets with applications in data mining, text recognition, dimension reduction, face…

Leveraging the vision foundation models has emerged as a mainstream paradigm that improves the performance of image feature matching. However, previous works have ignored the misalignment when introducing the foundation models into feature…

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

Recent advances in deep learning from probability distributions successfully achieve classification or regression from distribution samples, thus invariant under permutation of the samples. The first contribution of the paper is to extend…

Masked image modeling (MIM) learns representations with remarkably good fine-tuning performances, overshadowing previous prevalent pre-training approaches such as image classification, instance contrastive learning, and image-text…

Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT), by drastically reducing the need for large parallel data. Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence…

Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only…

Deep Convolution Neural Networks (CNNs) can easily be fooled by subtle, imperceptible changes to the input images. To address this vulnerability, adversarial training creates perturbation patterns and includes them in the training set to…

Various multi-instance learning (MIL) based approaches have been developed and successfully applied to whole-slide pathological images (WSI). Existing MIL methods emphasize the importance of feature aggregators, but largely neglect the…

It is well-known that deep neural networks (DNNs) have shown remarkable success in many fields. However, when adding an imperceptible magnitude perturbation on the model input, the model performance might get rapid decrease. To address this…

Multimodal LLM datasets are inherently heterogeneous, with significant data variability. Although each modality exhibits independent variability, sample-level entanglement makes it difficult to balance workloads across both modalities and…

Long-tailed imbalance distribution is a common issue in practical computer vision applications. Previous works proposed methods to address this problem, which can be categorized into several classes: re-sampling, re-weighting, transfer…

Recent advances in deep learning renewed the research interests in machine learning for Network Intrusion Detection Systems (NIDS). Specifically, attention has been given to sequential learning models, due to their ability to extract the…

Masked diffusion models (MDMs) have achieved notable progress in modeling discrete data, while their potential in molecular generation remains underexplored. In this work, we explore their potential and introduce the surprising result that…