Computer vision is one of our deepest areas, covering how machines learn to see, segment, and reason about images and video. Articles here range from convolutional and transformer based architectures to dense prediction tasks like detection and segmentation, with regular coverage of medical imaging where reliable vision models carry real clinical weight. The emphasis stays on what makes a method work and where it breaks, backed by the original research.
Almost every logit based distillation method shares an awkward design. You take the student’s ordinary cross entropy loss, bolt a distillation term onto it, and then spend hours tuning the single weight that decides how much each half matters. Turn…
PLD: List Wise Knowledge Distillation with Plackett-Luce Read More »
FixMatch is built around a deceptively simple idea. Take one unlabeled image, make two versions of it, one with a light augmentation such as a small crop or flip, and one with a heavy augmentation such as strong color distortion…
KD-FixMatch Fixes FixMatch’s Noisy Early Pseudo Labels Read More »
Semi supervised learning exists because labeling data is expensive and unlabeled data is cheap. Pseudo label methods try to make the most of that imbalance by having a model label its own unlabeled data, then training on those self generated…
How A Channel Based Ensemble Produces Cleaner Pseudo Labels Read More »
Change detection sounds simple on paper. Take two satellite images of the same location captured months or years apart, then mark every pixel where something meaningfully changed. In practice, building the training data for this task is one of the…
VLM Guidance Cuts Label Needs for Change Detection Read More »
Deep networks are hungry. They get better with more data, and that pattern holds across vision, language, and just about every other domain researchers have thrown at them. The catch is that raw data is cheap while labeled data is…
FixMatch Shows How Little Supervision Semi Supervised Learning Actually Needs Read More »
A radiologist in a busy teaching hospital reads maybe forty brain studies before lunch. Glioma, meningioma, pituitary adenoma, or nothing at all. Most of those calls are easy. A handful are not, and the hard ones tend to be hard…
What 99.62% Accuracy on Brain Tumor MRI Actually Means Read More »
A dermatologist looking at a mole under a dermatoscope is doing something a plain convolutional network struggles with. She is reading fine texture right at the border of the lesion while also holding the whole shape in mind at once,…
EG-VAN Explained, Dual Branch Attention for Skin Cancer Scans Read More »
Skin cancer is common enough, and dangerous enough when caught late, that the stakes for this kind of research are genuinely high. Melanoma’s ten year survival rate falls below 39 percent when it is detected at an advanced stage, according…
A Top Scoring Skin Cancer AI Missed Most Basal Cell Cases Read More »