Related papers: Zero-Ablation Overstates Register Content Dependen…

We present theoretical results of a low-loss all-optical switch based on electromagnetically induced transparency and the classical Zeno effect in a microdisk resonator. We show that a control beam can modify the atomic absorption of the…

We highlight a curious empirical result within modern Vision Transformers (ViTs). Specifically, self-attention catastrophically fails to train unless it is used in conjunction with a skip connection. This is in contrast to other elements of…

Fine-tuning pre-trained convolutional neural networks on ImageNet for downstream tasks is well-established. Still, the impact of model size on the performance of vision transformers in similar scenarios, particularly under label noise,…

Low dose computed tomography is a mainstream for clinical applications. How-ever, compared to normal dose CT, in the low dose CT (LDCT) images, there are stronger noise and more artifacts which are obstacles for practical applications. In…

In the era of foundation models, CLIP has emerged as a powerful tool for aligning text & visual modalities into a common embedding space. However, the alignment objective used to train CLIP often results in subpar visual features for…

Wind turbine blades operate in harsh environments, making timely damage detection essential for preventing failures and optimizing maintenance. Drone-based inspection and deep learning are promising, but typically depend on large, labeled…

The contemporary phenomenon of deepfakes, utilizing GAN or diffusion models for face swapping, presents a substantial and evolving threat in digital media, identity verification, and a multitude of other systems. The majority of existing…

Most change detection models based on vision transformers currently follow a "pretraining then fine-tuning" strategy. This involves initializing the model weights using large scale classification datasets, which can be either natural images…

Automated underwater species classification is constrained by annotation cost and environmental variation that limits the transferability of fully supervised models. Recent work has shown that frozen embeddings from self-supervised vision…

Stereo needs features that preserve fine cross view correspondence rather than only semantic similarity. Recent self supervised vision models transfer well, but they are not built for this goal, and geometry focused methods often rely on a…

The unsupervised image-to-image translation aims at finding a mapping between the source ($A$) and target ($B$) image domains, where in many applications aligned image pairs are not available at training. This is an ill-posed learning…

Vision Transformers rely on positional embeddings and class tokens encoding fixed spatial priors. While effective for natural images, these priors may be suboptimal when spatial layout is weakly informative, a frequent condition in medical…

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual grounding, establishing themselves as a general interface for various vision-language applications. This progress has driven the development of…

Vision Transformers (ViTs), when pre-trained on large-scale data, provide general-purpose representations for diverse downstream tasks. However, artifacts in ViTs are widely observed across different supervision paradigms and downstream…

Modern visual systems have a wide range of potential applications in vision tasks for natural science research, such as aiding in species discovery, monitoring animals in the wild, and so on. However, real-world vision tasks may experience…

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…

Recently, operator learning, or learning mappings between infinite-dimensional function spaces, has garnered significant attention, notably in relation to learning partial differential equations from data. Conceptually clear when outlined…

Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional benchmarks. We argue that this limitation may stem less from deficient representations…

Zero-Shot Learning (ZSL) promises to scale visual recognition by bypassing the conventional model training requirement of annotated examples for every category. This is achieved by establishing a mapping connecting low-level features and a…

Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero-shot transfer by…