Related papers: HYPE: Hyperbolic Entailment Filtering for Underspe…
Image labeling is an important task for training computer vision models. In specialized domains, such as healthcare, it is expensive and challenging to recruit specialists for image labeling. We propose HEPHA, a mixed-initiative image…
In convolutional neural networks (CNNs), downsampling operations are crucial to model performance. Although traditional downsampling methods (such as maximum pooling and cross-row convolution) perform well in feature aggregation, receptive…
Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the…
Contrastive Language-Image Pre-training (CLIP) has become the standard for cross-modal image-text representation learning. Improving CLIP typically requires additional data and retraining with new loss functions, but these demands raise…
We introduce a hyperbolic neural network approach to pixel-level active learning for semantic segmentation. Analysis of the data statistics leads to a novel interpretation of the hyperbolic radius as an indicator of data scarcity. In HALO…
We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperbolic space $\mathbb{H}^d$ to natively preserve the hierarchical tree topology of the human…
Natural language text exhibits hierarchical structure in a variety of respects. Ideally, we could incorporate our prior knowledge of this hierarchical structure into unsupervised learning algorithms that work on text data. Recent work by…
The black-box nature of deep learning models in NLP hinders their widespread application. The research focus has shifted to Hierarchical Attribution (HA) for its ability to model feature interactions. Recent works model non-contiguous…
The task of identifying multimodal image-text representations has garnered increasing attention, particularly with models such as CLIP (Contrastive Language-Image Pretraining), which demonstrate exceptional performance in learning complex…
With the development of multimodality and large language models, the deep learning-based technique for medical image captioning holds the potential to offer valuable diagnostic recommendations. However, current generic text and image…
Hypergraphs have been becoming a popular choice to model complex, non-pairwise, and higher-order interactions for recommender system. However, compared with traditional graph-based methods, the constructed hypergraphs are usually much…
Learning fine-grained embeddings from coarse labels is a challenging task due to limited label granularity supervision, i.e., lacking the detailed distinctions required for fine-grained tasks. The task becomes even more demanding when…
Hierarchical reinforcement learning deals with the problem of breaking down large tasks into meaningful sub-tasks. Autonomous discovery of these sub-tasks has remained a challenging problem. We propose a novel method of learning sub-tasks…
We introduce DIP, a novel unsupervised post-training method designed to enhance dense image representations in large-scale pretrained vision encoders for in-context scene understanding. Unlike prior approaches that rely on complex…
Within the realm of advanced code retrieval, existing methods have primarily relied on intricate matching and attention-based mechanisms. However, these methods often lead to computational and memory inefficiencies, posing a significant…
Electronic Health Records (EHR) have been heavily used in modern healthcare systems for recording patients' admission information to hospitals. Many data-driven approaches employ temporal features in EHR for predicting specific diseases,…
Finding a low dimensional representation of hierarchical, structured data described by a network remains a challenging problem in the machine learning community. An emerging approach is embedding these networks into hyperbolic space because…
Deep Learning is mostly responsible for the surge of interest in Artificial Intelligence in the last decade. So far, deep learning researchers have been particularly successful in the domain of image processing, where Convolutional Neural…
The challenges in recovering underwater images are the presence of diverse degradation factors and the lack of ground truth images. Although synthetic underwater image pairs can be used to overcome the problem of inadequately observing…
Most real-world datasets consist of a natural hierarchy between classes or an inherent label structure that is either already available or can be constructed cheaply. However, most existing representation learning methods ignore this…