Related papers: D3G: Diverse Demographic Data Generation Increases…

Accurate prediction with multimodal data-encompassing tabular, textual, and visual inputs or outputs-is fundamental to advancing analytics in diverse application domains. Traditional approaches often struggle to integrate heterogeneous data…

Neural networks struggle with image classification when biases are learned and misleads correlations, affecting their generalization and performance. Previous methods require attribute labels (e.g. background, color) or utilizes Generative…

High annotation costs are a substantial bottleneck in applying modern deep learning architectures to clinically relevant medical use cases, substantiating the need for novel algorithms to learn from unlabeled data. In this work, we propose…

Generalized zero-shot semantic segmentation of 3D point clouds aims to classify each point into both seen and unseen classes. A significant challenge with these models is their tendency to make biased predictions, often favoring the classes…

Deep learning has become a popular tool for medical image analysis, but the limited availability of training data remains a major challenge, particularly in the medical field where data acquisition can be costly and subject to privacy…

Unsupervised fine-grained class clustering is a practical yet challenging task due to the difficulty of feature representations learning of subtle object details. We introduce C3-GAN, a method that leverages the categorical inference power…

Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for image generation. However, it is unclear how meaningful the…

Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic…

CLIP is a widely used foundational vision-language model that is used for zero-shot image recognition and other image-text alignment tasks. We demonstrate that CLIP is vulnerable to change in image quality under compression. This surprising…

The synergy between generative and discriminative models receives growing attention. While discriminative Contrastive Language-Image Pre-Training (CLIP) excels in high-level semantics, it struggles with perceiving fine-grained visual…

Reconstructing and understanding 3D scenes from unposed sparse views in a feed-forward manner remains as a challenging task in 3D computer vision. Recent approaches use per-pixel 3D Gaussian Splatting for reconstruction, followed by a…

Accurate gender recognition from extreme long-range imagery remains a challenging problem due to limited spatial resolution, viewpoint variability, and loss of facial cues. For such purpose, we present a dual-path transformer framework that…

Given a query from one modality, few-shot cross-modal retrieval (CMR) retrieves semantically similar instances in another modality with the target domain including classes that are disjoint from the source domain. Compared with classical…

3D reconstruction from a single image is a long-standing problem in computer vision. Learning-based methods address its inherent scale ambiguity by leveraging increasingly large labeled and unlabeled datasets, to produce geometric priors…

CLIP (Contrastive Language-Image Pre-Training) has shown remarkable zero-shot transfer capabilities in cross-modal correlation tasks such as visual classification and image retrieval. However, its performance in cross-modal generation tasks…

Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductive setting. However, there is little work that explores the…

Few-shot image classification aims to accurately classify unlabeled images using only a few labeled samples. The state-of-the-art solutions are built by deep learning, which focuses on designing increasingly complex deep backbones.…

Multi-turn compositional image generation (M-CIG) is a challenging task that aims to iteratively manipulate a reference image given a modification text. While most of the existing methods for M-CIG are based on generative adversarial…

Data scarcity remains a critical bottleneck impeding technological advancements across various domains, including but not limited to medicine and precision agriculture. To address this challenge, we explore the potential of Deep Generative…

In the realm of Zero-Shot Learning (ZSL), we address biases in Generalized Zero-Shot Learning (GZSL) models, which favor seen data. To counter this, we introduce an end-to-end generative GZSL framework called D$^3$GZSL. This framework…