280 citations · 2k across the 81 of their papers we have counts for
3 papers · 1 filter
First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning
Aristeidis Panos, Yuriko Kobe, Daniel Olmeda Reino +2
In Class-Incremental Learning (CIL) an image classification system is exposed to new classes in each learning session and must be updated incrementally. Methods approaching this pr…
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image Classification
Massimiliano Patacchiola, John Bronskill, Aliaksandra Shysheya +3
Recent years have seen a growth in user-centric applications that require effective knowledge transfer across tasks in the low-data regime. An example is personalization, where a p…
Continual Novelty Detection
Rahaf Aljundi, Daniel Olmeda Reino, Nikolay Chumerin +1
Novelty Detection methods identify samples that are not representative of a model's training set thereby flagging misleading predictions and bringing a greater flexibility and tran…