1 code implementation • 14 Mar 2024 • Qinyu Zhao, Ming Xu, Kartik Gupta, Akshay Asthana, Liang Zheng, Stephen Gould
This study uses linear probing to shed light on the hidden knowledge at the output layer of LVLMs.
1 code implementation • 1 Feb 2024 • Qinyu Zhao, Ming Xu, Kartik Gupta, Akshay Asthana, Liang Zheng, Stephen Gould
Feature shaping refers to a family of methods that exhibit state-of-the-art performance for out-of-distribution (OOD) detection.
Out-of-Distribution Detection Out of Distribution (OOD) Detection
no code implementations • 9 Nov 2023 • Kartik Gupta, Akshay Asthana
While quantization-aware training QAT is the well-studied approach to quantize the networks at low precision, most research focuses on over-parameterized networks for classification with limited studies on popular and edge device friendly single-shot object detection and semantic segmentation methods like YOLO.
1 code implementation • 4 Aug 2023 • Ravikiran Parameshwara, Ibrahim Radwan, Akshay Asthana, Iman Abbasnejad, Ramanathan Subramanian, Roland Goecke
Whilst deep learning techniques have achieved excellent emotion prediction, they still require large amounts of labelled training data, which are (a) onerous and tedious to compile, and (b) prone to errors and biases.
no code implementations • 12 Jun 2023 • Soujanya Narayana, Ibrahim Radwan, Ravikiran Parameshwara, Iman Abbasnejad, Akshay Asthana, Ramanathan Subramanian, Roland Goecke
Whilst a majority of affective computing research focuses on inferring emotions, examining mood or understanding the \textit{mood-emotion interplay} has received significantly less attention.
1 code implementation • 18 Mar 2016 • Grigorios G. Chrysos, Epameinondas Antonakos, Patrick Snape, Akshay Asthana, Stefanos Zafeiriou
Recently, technologies such as face detection, facial landmark localisation and face recognition and verification have matured enough to provide effective and efficient solutions for imagery captured under arbitrary conditions (referred to as "in-the-wild").
no code implementations • CVPR 2014 • Akshay Asthana, Stefanos Zafeiriou, Shiyang Cheng, Maja Pantic
We propose very efficient strategies to update the model and we show that is possible to automatically construct robust discriminative person and imaging condition specific models 'in-the-wild' that outperform state-of-the-art generic face alignment strategies.
no code implementations • CVPR 2013 • Akshay Asthana, Stefanos Zafeiriou, Shiyang Cheng, Maja Pantic
We present a novel discriminative regression based approach for the Constrained Local Models (CLMs) framework, referred to as the Discriminative Response Map Fitting (DRMF) method, which shows impressive performance in the generic face fitting scenario.