Related papers: Balancing Multimodal Learning through Label Space …

Automated Machine Learning has grown very successful in automating the time-consuming, iterative tasks of machine learning model development. However, current methods struggle when the data is imbalanced. Since many real-world datasets are…

Visual reprogramming (VR) leverages the intrinsic capabilities of pretrained vision models by adapting their input or output interfaces to solve downstream tasks whose labels (i.e., downstream labels) might be totally different from the…

Multimodal Biomedical Image Incremental Learning (MBIIL) is essential for handling diverse tasks and modalities in the biomedical domain, as training separate models for each modality or task significantly increases inference costs.…

Multimodal models often converge to a dominant-modality solution, in which a stronger, faster-converging modality overshadows weaker ones. This modality imbalance causes suboptimal performance. Existing methods attempt to balance different…

Extreme multi-label classification aims to learn a classifier that annotates an instance with a relevant subset of labels from an extremely large label set. Many existing solutions embed the label matrix to a low-dimensional linear…

Multimodal learning faces two major challenges: modality imbalance and data noise, which significantly affect the robustness and generalization ability of models. Existing methods achieve modality balance by suppressing dominant modalities,…

In multiple instance multiple label learning, each sample, a bag, consists of multiple instances. To alleviate labeling complexity, each sample is associated with a set of bag-level labels leaving instances within the bag unlabeled. This…

Partial-label learning (PLL) is a peculiar weakly-supervised learning task where the training samples are generally associated with a set of candidate labels instead of single ground truth. While a variety of label disambiguation methods…

The label shift problem refers to the supervised learning setting where the train and test label distributions do not match. Existing work addressing label shift usually assumes access to an \emph{unlabelled} test sample. This sample may be…

The online emergence of multi-modal sharing platforms (eg, TikTok, Youtube) is powering personalized recommender systems to incorporate various modalities (eg, visual, textual and acoustic) into the latent user representations. While…

Video search has become the main routine for users to discover videos relevant to a text query on large short-video sharing platforms. During training a query-video bi-encoder model using online search logs, we identify a modality bias…

Multi-label recognition with partial labels (MLR-PL), in which only some labels are known while others are unknown for each image, is a practical task in computer vision, since collecting large-scale and complete multi-label datasets is…

Neural networks have recently been proposed for multi-label classification because they are able to capture and model label dependencies in the output layer. In this work, we investigate limitations of BP-MLL, a neural network (NN)…

In multi-label classification, the main focus has been to develop ways of learning the underlying dependencies between labels, and to take advantage of this at classification time. Developing better feature-space representations has been…

Multi-task learning (MTL) aims to improve the generalization of several related tasks by learning them jointly. As a comparison, in addition to the joint training scheme, modern meta-learning allows unseen tasks with limited labels during…

In many real-world tasks, particularly those involving data objects with complicated semantics such as images and texts, one object can be represented by multiple instances and simultaneously be associated with multiple labels. Such tasks…

Neural Networks can perform poorly when the training label distribution is heavily imbalanced, as well as when the testing data differs from the training distribution. In order to deal with shift in the testing label distribution, which…

The purpose of partial multi-label feature selection is to select the most representative feature subset, where the data comes from partial multi-label datasets that have label ambiguity issues. For label disambiguation, previous methods…

We address the challenge of minimizing true risk in multi-node distributed learning. These systems are frequently exposed to both inter-node and intra-node label shifts, which present a critical obstacle to effectively optimizing model…

Meta-learning is an effective method to handle imbalanced and noisy-label learning, but it depends on a validation set containing randomly selected, manually labelled and balanced distributed samples. The random selection and manual…