Related papers: SUMix: Mixup with Semantic and Uncertain Informati…

Existing pretraining data mixing methods for large language models (LLMs) typically follow a domain-wise methodology, a top-down process that first determines domain weights and then performs uniform data sampling across each domain.…

Data augmentation is one of the regularization strategies for the training of deep learning models, which enhances generalizability and prevents overfitting, leading to performance improvement. Although researchers have proposed various…

In computational pathology, researchers often face challenges due to the scarcity of labeled pathology datasets. Data augmentation emerges as a crucial technique to mitigate this limitation. In this study, we introduce an efficient data…

This paper introduces MixDiff, a new self-supervised learning (SSL) pre-training framework that combines real and synthetic images. Unlike traditional SSL methods that predominantly use real images, MixDiff uses a variant of Stable…

Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches. However, it is challenging to fully leverage different modalities due to practical challenges…

Based on the observation that semantic segmentation errors are partially predictable, we propose a compact formulation using confusion statistics of the trained classifier to refine (re-estimate) the initial pixel label hypotheses. The…

State-of-the-art video action classifiers often suffer from overfitting. They tend to be biased towards specific objects and scene cues, rather than the foreground action content, leading to sub-optimal generalization performances. Recent…

Semi-supervised techniques have removed the barriers of large scale labelled set by exploiting unlabelled data to improve the performance of a model. In this paper, we propose a semi-supervised deep multi-task classification and…

Patch-level data augmentation techniques such as Cutout and CutMix have demonstrated significant efficacy in enhancing the performance of vision tasks. However, a comprehensive theoretical understanding of these methods remains elusive. In…

Large deep networks have demonstrated competitive performance in single image super-resolution (SISR), with a huge volume of data involved. However, in real-world scenarios, due to the limited accessible training pairs, large models exhibit…

Semantic noise in image classification datasets, where visually similar categories are frequently mislabeled, poses a significant challenge to conventional supervised learning approaches. In this paper, we explore the potential of using…

Generalizable person re-identification (Re-ID) aims to recognize individuals across unseen cameras and environments. While existing methods rely heavily on limited labeled multi-camera data, we propose DynaMix, a novel method that…

A recently-proposed technique called self-adaptive training augments modern neural networks by allowing them to adjust training labels on the fly, to avoid overfitting to samples that may be mislabeled or otherwise non-representative. By…

Respiratory sound classification plays a pivotal role in diagnosing respiratory diseases. While deep learning models have shown success with various respiratory sound datasets, our experiments indicate that models trained on one dataset…

Recently contrastive learning has shown significant progress in learning visual representations from unlabeled data. The core idea is training the backbone to be invariant to different augmentations of an instance. While most methods only…

In computer vision, depth estimation is crucial for domains like robotics, autonomous vehicles, augmented reality, and virtual reality. Integrating semantics with depth enhances scene understanding through reciprocal information sharing.…

Semi-supervised learning, i.e. jointly learning from labeled and unlabeled samples, is an active research topic due to its key role on relaxing human supervision. In the context of image classification, recent advances to learn from…

Modern person re-identification (Re-ID) methods have a weak generalization ability and experience a major accuracy drop when capturing environments change. This is because existing multi-camera Re-ID datasets are limited in size and…

The rise in internet usage has led to the generation of massive amounts of data, resulting in the adoption of various supervised and semi-supervised machine learning algorithms, which can effectively utilize the colossal amount of data to…

Semi-Supervised Learning (SSL) algorithms have shown great potential in training regimes when access to labeled data is scarce but access to unlabeled data is plentiful. However, our experiments illustrate several shortcomings that prior…