Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Kalla, Jayateja"'
Autor:
Chudasama, Vishal, Sarkar, Hiran, Wasnik, Pankaj, Balasubramanian, Vineeth N, Kalla, Jayateja
Object detection is a critical field in computer vision focusing on accurately identifying and locating specific objects in images or videos. Traditional methods for object detection rely on large labeled training datasets for each object category, w
Externí odkaz:
http://arxiv.org/abs/2408.14249
Autor:
Kalla, Jayateja, Biswas, Soma
This paper investigates the impact of self-supervised learning, specifically image rotations, on various class-incremental learning paradigms. Here, each image with a predefined rotation is considered as a new class for training. At inference, all im
Externí odkaz:
http://arxiv.org/abs/2408.04347
We propose a novel TACLE (TAsk and CLass-awarE) framework to address the relatively unexplored and challenging problem of exemplar-free semi-supervised class incremental learning. In this scenario, at each new task, the model has to learn new classes
Externí odkaz:
http://arxiv.org/abs/2407.08041
Autor:
Kalla, Jayateja, Biswas, Soma
This paper introduces a two-stage framework designed to enhance long-tail class incremental learning, enabling the model to progressively learn new classes, while mitigating catastrophic forgetting in the context of long-tailed data distributions. Ad
Externí odkaz:
http://arxiv.org/abs/2311.01227
Autor:
Kalla, Jayateja, Biswas, Soma
Few-shot class-incremental learning (FSCIL) aims to learn progressively about new classes with very few labeled samples, without forgetting the knowledge of already learnt classes. FSCIL suffers from two major challenges: (i) over-fitting on the new
Externí odkaz:
http://arxiv.org/abs/2307.02246
Publikováno v:
Multimedia Tools & Applications; Feb2024, Vol. 83 Issue 5, p13707-13723, 17p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.