This paper tackles the problem of semi-supervised learning when set labeled samples is limited to a small number images per class, typically less than 10, that we refer as barely-supervised learning. We analyze in depth behavior state-of-the-art method, FixMatch, which relies on weakly-augmented version an image obtain supervision signal for more strongly-augmented version. show it frequently f...

We study words that barely avoid repetitions, for several senses of "barely". A squarefree (respectively, overlap-free, cubefree) word is irreducible if removing any one its interior letters creates a square overlap, cube). delicate changing classify the lengths and squarefree, cubefree over binary ternary alphabets.