1 citations · 3 across the 3 of their papers we have counts for
4 papers
σ-GPTs: A New Approach to Autoregressive Models
Arnaud Pannatier, Evann Courdier, François Fleuret
Autoregressive models, such as the GPT family, use a fixed order, usually left-to-right, to generate sequences. However, this is not a necessity. In this paper, we challenge this a…
PAUMER: Patch Pausing Transformer for Semantic Segmentation
Evann Courdier, Prabhu Teja Sivaprasad, François Fleuret
We study the problem of improving the efficiency of segmentation transformers by using disparate amounts of computation for different parts of the image. Our method, PAUMER, accomp…
Borrowing from yourself: Faster future video segmentation with partial channel update
Evann Courdier, François Fleuret
Semantic segmentation is a well-addressed topic in the computer vision literature, but the design of fast and accurate video processing networks remains challenging. In addition, t…
Real-Time Segmentation Networks should be Latency Aware
Evann Courdier, Francois Fleuret
As scene segmentation systems reach visually accurate results, many recent papers focus on making these network architectures faster, smaller and more efficient. In particular, stu…