Related papers: Contrastive Image-Metadata Pre-Training for Materi…
Contrastive learning has emerged as a prominent branch of self-supervised learning for several years. Especially, CLIP, which applies contrastive learning to large sets of captioned images, has garnered significant attention. Recently,…
Deep learning has demonstrated significant improvements in medical image segmentation using a sufficiently large amount of training data with manual labels. Acquiring well-representative labels requires expert knowledge and exhaustive…
Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks. However, CLIP is quite…
Multi-pass transmission electron microscopy (MPTEM) has been proposed as a way to reduce damage to radiation-sensitive materials. For the field of cryo-electron microscopy (cryo-EM), this would significantly reduce the number of projections…
Ptychography provides highly efficient imaging in scanning transmission electron microscopy (STEM), but questions have remained over its applicability to strongly scattering samples such as those most commonly seen in materialsscience.…
Recent advancements in neural compression have surpassed traditional codecs in PSNR and MS-SSIM measurements. However, at low bit-rates, these methods can introduce visually displeasing artifacts, such as blurring, color shifting, and…
The transmission electron microscope (TEM) has become an essential tool for innovation in nanoscience, material science, and biology. Despite these instruments being widely used across both industry and academia, academics may hesitate to…
By means of numerical simulations, we demonstrate the innovative use of computational ghost imaging in transmission electron microscopy to retrieve images with a resolution that overcomes the limitations imposed by coherent aberrations. The…
State-of-the-art pre-trained image models predominantly adopt a two-stage approach: initial unsupervised pre-training on large-scale datasets followed by task-specific fine-tuning using Cross-Entropy loss~(CE). However, it has been…
Contrastive Language and Image Pairing (CLIP), a transformative method in multimedia retrieval, typically trains two neural networks concurrently to generate joint embeddings for text and image pairs. However, when applied directly, these…
Contrastive Language-Image Pre-training (CLIP) on large-scale image-caption datasets learns representations that can achieve remarkable zero-shot generalization. However, such models require a massive amount of pre-training data. Improving…
In a standard computed tomography (CT) image, pixels having the same Hounsfield Units (HU) can correspond to different materials and it is therefore challenging to differentiate and quantify materials. Dual-energy CT (DECT) is desirable to…
Developing artificial intelligence (AI) and machine learning (ML) models for medical imaging typically involves extensive training and testing on large datasets, consuming significant computational time, energy, and resources. There is a…
We propose DepthTCM, a physics-aware end-to-end framework for depth map compression. In our framework of DepthTCM, the high-bit depth map is first converted to a conventional 3-channel image representation losslessly using a method inspired…
We propose a semantic similarity metric for image registration. Existing metrics like euclidean distance or normalized cross-correlation focus on aligning intensity values, giving difficulties with low intensity contrast or noise. Our…
Retinal implants aim to restore functional vision despite photoreceptor degeneration, yet are fundamentally constrained by low resolution electrode arrays and patient-specific perceptual distortions. Most deployed encoders rely on…
This paper studies cross-domain lossy compression through the lens of minimum entropy coupling (MEC) with rate and classification constraints. In this setting, an encoder observes samples from a degraded source domain, while the decoder is…
A new material characterization technique is emerging for the transmission electron microscope (TEM). Using electron energy-loss spectroscopy, real space mappings of the underlying electronic transitions in the sample, so called orbital…
Scanning transmission electron microscopy (STEM) has advanced rapidly in the last decade thanks to the ability to correct the major aberrations of the probe forming lens. Now atomic-sized beams are routine, even at accelerating voltages as…
Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts…