Prompt learning adapts vision-language models such as CLIP by optimizing a short learnable prompt. The cross-entropy objective pulls this prompt toward base-class specialization, whereas generalization to unseen classes benefits from staying close to CLIP's zero-shot feature space. Because both objectives act on the sa...
Attention is known to be sparse in vision transformers. In particular, we analyze the unequal relevance of attention-matrix columns to the final computation and show that this phenomenon becomes increasingly pronounced with network depth. This can be interpreted as saying that tokens have an absolute importance for the...
Charles Herr, Gabriele Spadaro, Enzo Tartaglione· 0 citations
Routing and switch placement are fundamental combinatorial optimization problems in chip design, requiring the joint optimization of routing topology and physical placement under strict structural, geometric and logical constraints. Existing approaches typically rely on carefully engineered heuristics that incorporate...
Dorian Gailhard, Ugo Lecerf, Enzo Tartaglione et al.· 0 citations
CutClean is a privacy-aware pruning method that allows to reduce privacy information flow through the network, while increasing its sparsity, and effectively minimizes private information flow while achieving high sparsity rates and preserving classification target accuracy.
Leonardo Magliolo, Vito Paolo Pastore, Giuseppe Valenzise et al.· International Conference on...· 0 citations
This work proposes an efficient strategy that enables merging of layers without an existing analytical solution, and also without increasing kernel size, and validate the approach across multiple architectures and datasets, and measure inference speed-up gains on real embedded platforms.
P. Shul'zhenko, Gabriele Spadaro, Enzo Tartaglione· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.