Related papers: GeneCIS: A Benchmark for General Conditional Image…

Vision-language contrastive learning frameworks such as CLIP enable learning representations from natural language supervision and provide strong zero-shot classification capabilities. However, due to the nature of the supervisory signal in…

Vision-language foundation models have been incredibly successful in a wide range of downstream computer vision tasks using adaptation methods. However, due to the high cost of obtaining pre-training datasets, pairs with weak image-text…

Human pose estimators are typically retrained from scratch or naively fine-tuned whenever keypoint sets, sensing modalities, or deployment domains change--an inefficient, compute-intensive practice that rarely matches field constraints. We…

When it comes to deploying deep vision models, the behavior of these systems must be explicable to ensure confidence in their reliability and fairness. A common approach to evaluate deep learning models is to build a labeled test set with…

As advanced image manipulation techniques emerge, detecting the manipulation becomes increasingly important. Despite the success of recent learning-based approaches for image manipulation detection, they typically require expensive…

The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard…

Computer vision models have known performance disparities across attributes such as gender and skin tone. This means during tasks such as classification and detection, model performance differs for certain classes based on the demographics…

In unsupervised domain adaptation (UDA), a model trained on source data (e.g. synthetic) is adapted to target data (e.g. real-world) without access to target annotation. Most previous UDA methods struggle with classes that have a similar…

We address the problem of generalized zero-shot semantic segmentation (GZS3) predicting pixel-wise semantic labels for seen and unseen classes. Most GZS3 methods adopt a generative approach that synthesizes visual features of unseen classes…

What makes images similar? To measure the similarity between images, they are typically embedded in a feature-vector space, in which their distance preserve the relative dissimilarity. However, when learning such similarity embeddings the…

The concept of image similarity is ambiguous, and images can be similar in one context and not in another. This ambiguity motivates the creation of metrics for specific contexts. This work explores the ability of deep perceptual similarity…

Fine-grained visual categorization (FGVC), which aims at classifying objects with small inter-class variances, has been significantly advanced in recent years. However, ultra-fine-grained visual categorization (ultra-FGVC), which targets at…

Pretrained vision-language models, such as CLIP, show promising zero-shot performance across a wide variety of datasets. For closed-set classification tasks, however, there is an inherent limitation: CLIP image encoders are typically…

Few-shot image classification remains challenging due to the scarcity of labeled training examples. Augmenting them with synthetic data has emerged as a promising way to alleviate this issue, but models trained on synthetic samples often…

Image captioning aims at generating descriptive and meaningful textual descriptions of images, enabling a broad range of vision-language applications. Prior works have demonstrated that harnessing the power of Contrastive Image Language…

Evaluating generative models for synthetic medical imaging is crucial yet challenging, especially given the high standards of fidelity, anatomical accuracy, and safety required for clinical applications. Standard evaluation of generated…

Many real-world tasks require models to compare images along multiple similarity conditions (e.g. similarity in color, category or shape). Existing methods often reason about these complex similarity relationships by learning…

Generalized zero-shot learning aims to recognize both seen and unseen classes with the help of semantic information that is shared among different classes. It inevitably requires consistent visual-semantic alignment. Existing approaches…

In image recognition, there are many cases where training samples cannot cover all target classes. Zero-shot learning (ZSL) utilizes the class semantic information to classify samples of the unseen categories that have no corresponding…

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…