no code implementations • 1 Sep 2016 • Siavash Gorji, James J. Clark
We present a novel visual attention tracking technique based on Shared Attention modeling.
1 code implementation • 20 Apr 2017 • Qing Tian, Tal Arbel, James J. Clark
Many real-time tasks, such as human-computer interaction, require fast and efficient facial gender classification.
no code implementations • CVPR 2017 • Siavash Gorji, James J. Clark
The Attentional Push CNN is then fine-tuned along with the augmented saliency CNN to minimize the Euclidean distance between the augmented saliency and ground truth fixations using an eye-tracking dataset, annotated with the head and the gaze location of the scene actors.
no code implementations • 21 Nov 2017 • Bingqing Yu, James J. Clark
The WAYLA approach is based on the Conditional Generative Adversarial Network (Conditional GAN) image-to-image translation technique of Isola et al. We consider two specific applications - the first, of reconstructing newspaper images from gaze heat maps, and the second, of detailed reconstruction of images containing only text.
no code implementations • 21 Nov 2017 • Bingqing Yu, James J. Clark
The discriminator also has the observer label as an input, which contributes to the personalization ability of our approach.
1 code implementation • 21 Mar 2018 • Qing Tian, Tal Arbel, James J. Clark
Moreover, we examine our approach's potential in network architecture search for specific tasks and analyze the influence of our pruning on model robustness to noises and adversarial attacks.
no code implementations • CVPR 2018 • Siavash Gorji, James J. Clark
We evaluate our model by comparing the performance of several augmented static saliency models with state-of-the-art in spatiotemporal saliency on three largest dynamic eye tracking datasets, HOLLYWOOD2, UCF-Sport and DIEM.
1 code implementation • 10 Apr 2019 • Guanqing Hu, James J. Clark
In order to achieve automatic compositing in natural scenes, we propose a fully automated method that integrates instance segmentation and image matting processes to generate high-quality semantic mattes that can be used for image editing task.
no code implementations • 29 Sep 2020 • Qing Tian, Tal Arbel, James J. Clark
We also show that our grown Inception nets (without hard-coded dimension alignment) clearly outperform residual nets of similar complexities.
no code implementations • 1 Jan 2021 • Samrudhdhi Bharatkumar Rangrej, James J. Clark
Unlike in the deep convolution network, in hard attention it is explainable which regions of the image contributed to the prediction.
1 code implementation • 30 Mar 2021 • Saverio Vadacchino, Raghav Mehta, Nazanin Mohammadi Sepahvand, Brennan Nichyporuk, James J. Clark, Tal Arbel
The proposed network is trained and tested on the BraTS 2019 brain tumour segmentation challenge dataset, where it achieves performance improvements in the ranges of 16% - 26% over (a) recent modality-agnostic segmentation methods (U-HeMIS, U-HVED), (b) KD-Net adapted to this problem, (c) the pre-trained student network and (d) a non-hierarchical version of the network (AD-Net), in terms of Dice scores for enhancing tumour (ET).
no code implementations • 1 Apr 2021 • Samrudhdhi B. Rangrej, James J. Clark
The next fixation is planned using uncertainty in the content of the imagined scenes.
no code implementations • ACL 2022 • Ali Edalati, Marzieh Tahaei, Ahmad Rashid, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh
GPT is an auto-regressive Transformer-based pre-trained language model which has attracted a lot of attention in the natural language processing (NLP) domain due to its state-of-the-art performance in several downstream tasks.
1 code implementation • 15 Nov 2021 • Samrudhdhi B. Rangrej, James J. Clark
A visual hard attention model actively selects and observes a sequence of subregions in an image to make a prediction.
no code implementations • 24 Feb 2022 • Amir Ardakani, Arash Ardakani, Brett Meyer, James J. Clark, Warren J. Gross
Quantization of deep neural networks is a promising approach that reduces the inference cost, making it feasible to run deep networks on resource-restricted devices.
1 code implementation • CVPR 2022 • Samrudhdhi B. Rangrej, Chetan L. Srinidhi, James J. Clark
Most hard attention models initially observe a complete scene to locate and sense informative glimpses, and predict class-label of a scene based on glimpses.
no code implementations • 3 May 2022 • Danilo Vucetic, Mohammadreza Tayaranian, Maryam Ziaeefard, James J. Clark, Brett H. Meyer, Warren J. Gross
FAR reduces fine-tuning time on the DistilBERT model and CoLA dataset by 30%, and time spent on memory operations by 47%.
no code implementations • 5 Jul 2022 • Rezvan Sherkati, James J. Clark
We present a new method for image salience prediction, Clustered Saliency Prediction.
no code implementations • 3 Aug 2022 • Danilo Vucetic, Mohammadreza Tayaranian, Maryam Ziaeefard, James J. Clark, Brett H. Meyer, Warren J. Gross
We introduce Learner modules and priming, novel methods for fine-tuning that exploit the overparameterization of pre-trained language models to gain benefits in convergence speed and resource utilization.
no code implementations • 15 Sep 2022 • Ibtihel Amara, Maryam Ziaeefard, Brett H. Meyer, Warren Gross, James J. Clark
Knowledge distillation (KD) is an effective tool for compressing deep classification models for edge devices.
1 code implementation • 28 Sep 2022 • Manoosh Samiei, James J. Clark
Visual Search is referred to the task of finding a target object among a set of distracting objects in a visual display.
1 code implementation • 27 Oct 2022 • Manoosh Samiei, James J. Clark
Our second approach is object-based and predicts the distractor and target objects during visual search.
no code implementations • 20 Dec 2022 • Ali Edalati, Marzieh Tahaei, Ivan Kobyzev, Vahid Partovi Nia, James J. Clark, Mehdi Rezagholizadeh
We apply the proposed methods for fine-tuning T5 on the GLUE benchmark to show that incorporating the Kronecker-based modules can outperform state-of-the-art PET methods.
no code implementations • 25 Dec 2022 • Ibtihel Amara, Nazanin Sepahvand, Brett H. Meyer, Warren J. Gross, James J. Clark
We show that adaptively balancing between the reverse and forward divergences shifts the focus of the training strategy to the compact student network without limiting the teacher network's learning process.
no code implementations • 22 Jan 2024 • Lulan Shen, Ali Edalati, Brett Meyer, Warren Gross, James J. Clark
It is important to investigate the robustness of compressed networks in two types of data distribution shifts: domain shifts and adversarial perturbations.
no code implementations • 24 Jan 2024 • Lulan Shen, Ali Edalati, Brett Meyer, Warren Gross, James J. Clark
This paper describes a simple yet effective technique for refining a pretrained classifier network.
no code implementations • 2 Feb 2024 • Mohammadreza Tayaranian, Seyyed Hasan Mozafari, James J. Clark, Brett Meyer, Warren Gross
In this work, we improve upon the inference latency of the state-of-the-art methods by removing the floating-point operations, which are associated with the GELU activation in Swin Transformer.
no code implementations • 10 Mar 2024 • Youyuan Zhang, Xuan Ju, James J. Clark
By leveraging the self-consistency property of CMs, we eliminate the need for time-consuming inversion or additional condition extraction, reducing editing time.