image classification

A translator at the negotiating table doesn't listen to every word; they grasp the meaning of whole phrases. Electron microscopy poses a similar challenge: you need to figure out the crystal's thickness and its tilt in the beam, and all you have is a diffraction pattern, a mosaic of thousands of bright and dark spots.

At night on a volcano summit, six telescopes stare at the same speck of light. Each catches its own copy of the wave, and if you combine their signals, you get an image that no single instrument could produce alone. But there's a catch: light captured by different stations cannot simply be added like photographs.

Getting lost in a hall of mirrors is easy: every wall reflects another, and you feel like you've been here before. The brain gets similarly confused when surrounded by many similar places. Neurons responsible for the spatial map can fire the same signal for two different corners of a room. This is called spatial ambiguity.

Galaxy NGC 4254 lies 1.5 million light-years from the center of the Virgo cluster. It drags a long stream of cooling hydrogen — a sign that it's plowing headlong into the hot gas. Losing cold fuel quenches the birth of new stars.

Four faint streaks on an image — that's all an astronomer sees. Like a sculptor reconstructing the shape of invisible glass from four shadows.

Assembling the puzzle of the Universe, astronomers are used to every new detail fitting perfectly into the already completed picture. But sometimes there are pieces that seem cut from another jigsaw. Twenty thousand active galactic nuclei, and eleven percent of them the neural network confidently rejects as alien.

The optical sky background is a cosmic palimpsest, where light from billions of unresolved galaxies is layered, each layer corresponding to a different epoch. Until now we could only distinguish the brightest "letters"—individual stars and nearby galaxies.

Ordinary radar marks a drone as just a dot. A new method turns radio echoes into a volumetric sculpture: the signal outlines shape, tilt, and motion.

Radio signals in a room act just like sound in a concert hall: bouncing off walls and objects, they create a unique pattern — a silent melody for every location. Your phone, like a keen ear, catches this melody amid noise and distortion. It remembers which chord matches the corner of the couch, and which one fits the doorway.

A single-pixel camera works like an artist creating a picture through a stencil with many holes. In each frame, only a portion of the light, modulated by a mask, a spatial light modulator, reaches the single sensor, and then the computer reconstructs the full image by assembling this mosaic with computational algorithms.

A child exploring an unfamiliar apartment crawls from object to object and remembers what is visible from each corner. This is how the brain builds a mental map — an internal model of space. The gradCSCG algorithm works on the same principle: it receives a video stream from a camera and independently draws a map of the room, relying only on the changing images.

Medical scans are maps of tissue density. The brightness of each pixel reveals what’s there, much like photometry measures light intensity. But conventional algorithms analyze pixels in isolation, producing jagged organ boundaries. A new approach compels the program to prioritize smoothness.

Researchers took 16 everyday activities — from washing dishes to squatting — and broke the movements down into elementary components, much like a spectroscope splits light into a spectrum. Comparing three approaches, they found an unexpected key to recognition: a single averaged snapshot is enough. Only nine joints out of dozens carried the crucial information — the rest hardly mattered.

Look into the night sky — before you is not a scattering of lights, but a multi-layered manuscript. Under the bright ink of stars and galaxies appears a faded, almost erased text.

Ever since Einstein predicted gravitational lensing, and gravitational waves were first heard by LIGO detectors, physicists have dreamed of catching the lensed echo — a repeating signal from one merger, multiplied by the gravity of a massive body.

Almost a century after Фриц Цвикки suspected something was amiss in the motion of galaxies in the Coma cluster, and Вера Рубин measured stellar velocities in spiral arms, the nature of тёмной материи remains one of the most vexing mysteries.

Engineers create an alloy for solar concentrators by adding hard particles — like raisins in dough, to help it hold its shape under extreme heat. Too big a raisin and the material cracks. Previously, scientists manually counted these particles on microscope images.

An ordinary photo editor highlights objects in an image. The ZooBot:3D neural network works with distant galaxies like a cartographer drawing a map of an unexplored land.

Spacetime is often pictured as a smooth fabric. But at the very microscopic level, this fabric might not be continuous; instead, it could consist of individual 'atoms'—events linked by causality. This picture of the world is called causal set theory.

An artist paints a portrait stroke by stroke, and then someone offers them a flash camera — one click, and it's done. That's roughly the shift from multi-step models to one-step models in generating images of galaxies. Typical neural networks for image synthesis work like a watercolorist: they apply a layer, blur it, add details.

You're trying a dish at a restaurant, but you haven't seen the menu. You ask the waiter questions — too salty? what spices?—and from the answers you try to guess what kind of chef prepared it.

A biologist looks through a microscope at dozens of tiny cell spheres — spheroids. From these, miniature organ-like structures will later grow. The task is similar to a baker's job of checking whether the dough has risen evenly in each mold. Only here, instead of molds, there's a nutrient medium, and instead of dough, there are living cells.

Astronomers occasionally spot interstellar objects — rocky chunks or comets from other star systems. Most look ordinary, but some puzzle us with their shape, speed, or shine. To stop guessing, scientists applied the Loeb scale: from 0 (plain rock) to 5 (technosignature — an artificial signal from space).

A city map: intersections are nodes, streets are connections. For an algorithm to understand the structure, each node needs a label. The classical approach — standard model — assigns simple tags, like house numbers.

A mole on your skin looks like a mosaic of colored pieces. Each piece is a small patch of the image where color and texture barely change. Such pieces are called superpixels. If you connect them with lines, you get a network that looks like a subway map: stations are the pieces, and lines are the connections between them. The weight of each line shows how strongly two pieces are related.

A galaxy is not just a sprinkle of stars. At the center of many, something shines brighter than billions of suns: hot gas falling into a black hole. The color of this glow reveals what kind of life the galaxy leads — quietly birthing stars or violently consuming matter.

An ECG is not just a wavy line on paper. Like a diary, it records the state of the entire heart: rhythm, wall thickness, and hints of future problems. But currently, programs that learn to read this diary are trained on very narrow tasks — mostly detecting arrhythmias. That's like teaching someone to understand a book by showing them only a list of typos.

A magnetic film divided into tiny arrow-shaped cells behaves like a crowd in a square. While it's cold, all arrows point in the same direction — perfect order. Heat the film, and the arrows start darting around like pedestrians who have lost their purpose. Somewhere between these extremes, there is a moment when the system stops being uniform but hasn't yet dissolved into random noise.

A mass spectrometer works like a molecular shredder: it breaks a substance into charged fragments and weighs each one. From this 'fingerprint,' chemists can tell what was in the sample. But if the molecule is new and its fragments don't match anything known, the instrument just shows a set of peaks, and what lies behind them is a mystery. The authors of the paper proposed a workaround.

An ornithologist in the jungle hears a trill, but the bird is hidden in the foliage. It would be great to get its portrait right away — at least from a photo database. Usually, that requires thousands of pairs of “song recording + photo of the same bird,” and collecting them is expensive and time-consuming. The authors took a detour: they used two ready-made models.

For years, an X-ray telescope in orbit recorded how binary systems shine, where an ordinary star orbits a black hole or a neutron star. Matter from the companion falls onto the compact object, heats up to millions of degrees, and emits X-rays.

A galaxy cluster's gravity warps spacetime, acting like a colossal lens: it focuses and amplifies light from distant objects, as predicted by Einstein. Such lenses are rare, but they let us glimpse what lurks at the edges of the cosmos.

Graphs are considered identical if their 'terrain' matches. Imagine two maps with mountains and valleys: even if drawn differently, the heights and steepness of slopes can be the same.

An electrocardiogram is like a musical score, where each note is a heartbeat. A doctor hears the melody and spots the off-notes — arrhythmia. But listening to the score for hours is tiring, so a smart monitor is placed by the patient's bedside.

Entangled photons are like twins: what affects one instantly affects the other, even if they are separated by kilometers. Until recently, observing such a connection required detectors that counted each photon individually in pitch darkness. Physicists simplified the task by swapping them out for a regular scientific camera.

Usually, to understand a quantum state of light, you need to perform dozens of complex measurements, like trying all the keys on a keychain. The new AI model works differently: it's a universal key that, after a slight adjustment, opens many 'locks'—simple and the most tricky states.

Astronomers read the history of galaxies by their portraits. Previously, they used either lengthy analysis of light by colors or quick filtered snapshots, losing the details of shape.

An optician turns the frame, adjusts the focus, and a blurry spot becomes a sharp image. The new algorithm GOAL works much the same way: it rotates the data cloud, compresses redundant dimensions, and brings into focus what truly matters.

Two images of the same place: one taken in the morning from a drone, the other in the evening from a satellite. The first shows shadows from trees, the second shows glints on the water. It's like two accounts of the same event in different dialects: the words are similar, but the grammar is different.