Related papers: Selectively Hard Negative Mining for Alleviating G…

Pairwise ranking models have been widely used to address recommendation problems. The basic idea is to learn the rank of users' preferred items through separating items into \emph{positive} samples if user-item interactions exist, and…

Temporal grounding aims to localize a video moment which is semantically aligned with a given natural language query. Existing methods typically apply a detection or regression pipeline on the fused representation with the research focus on…

Securing a sufficient amount of paired data is important to train an image-text retrieval (ITR) model, but collecting paired data is very expensive. To address this issue, in this paper, we propose an active learning algorithm for ITR that…

Learning rates in stochastic neural network training are currently determined a priori to training, using expensive manual or automated iterative tuning. This study proposes gradient-only line searches to resolve the learning rate for…

Stochastic gradient descent algorithms for training linear and kernel predictors are gaining more and more importance, thanks to their scalability. While various methods have been proposed to speed up their convergence, the model selection…

The hubness problem widely exists in high-dimensional embedding space and is a fundamental source of error for cross-modal matching tasks. In this work, we study the emergence of hubs in Visual Semantic Embeddings (VSE) with application to…

Semantic segmentation has recently witnessed great progress. Despite the impressive overall results, the segmentation performance in some hard areas (e.g., small objects or thin parts) is still not promising. A straightforward solution is…

Vision-Language Models require efficient adaptation to continually emerging downstream tasks. While Parameter-Efficient Fine-Tuning mitigates catastrophic forgetting, assigning isolated modules per task leads to parameter explosion.…

Matching model is essential for Image-Text Retrieval framework. Existing research usually train the model with a triplet loss and explore various strategy to retrieve hard negative sentences in the dataset. We argue that current…

Generative feature matching network (GFMN) is an approach for training implicit generative models for images by performing moment matching on features from pre-trained neural networks. In this paper, we present new GFMN formulations that…

Gradient-based iterative optimization methods are the workhorse of modern machine learning. They crucially rely on careful tuning of parameters like learning rate and momentum. However, one typically sets them using heuristic approaches…

Automatic human matting is highly desired for many real applications. We investigate recent human matting methods and show that common bad cases happen when semantic human segmentation fails. This indicates that semantic understanding is…

Although the word-popularity based negative sampler has shown superb performance in the skip-gram model, the theoretical motivation behind oversampling popular (non-observed) words as negative samples is still not well understood. In this…

Given a relation and a ranking of its tuples, but no information about the ranking function, we are interested in synthesizing simple scoring functions that reproduce the ranking. Our system RankHow identifies linear scoring functions that…

Self-supervised representation learning has been extremely successful in medical image analysis, as it requires no human annotations to provide transferable representations for downstream tasks. Recent self-supervised learning methods are…

Since the recognition in the early nineties of the vanishing/exploding (V/E) gradient issue plaguing the training of neural networks (NNs), significant efforts have been exerted to overcome this obstacle. However, a clear solution to the…

In this paper, we present modifications of the iterative hard thresholding (IHT) method for recovery of jointly row-sparse and low-rank matrices. In particular a Riemannian version of IHT is considered which significantly reduces…

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

Subtle semantic differences in retinal image and text data present great challenges for pre-training visual-language models. Moreover, false negative samples, i.e., image-text pairs having the same semantics but incorrectly regarded as…