Search Results for author:
Found 30 papers, 9 papers with code
Automatic Pruning of Fine-tuning Datasets for Transformer-based Language Models
Our experiments on 5 downstream tasks and 2 language models show that, on average, fine-tuning on the winning ticket subsets results in a $0. 1 \%$ increase in the evaluation performance of the model.
Design Editing for Offline Model-based Optimization
Offline model-based optimization (MBO) aims to maximize a black-box objective function using only an offline dataset of designs and scores.
FastVideoEdit: Leveraging Consistency Models for Efficient Text-to-Video Editing
By leveraging the self-consistency property of CMs, we eliminate the need for time-consuming inversion or additional condition extraction, reducing editing time.
Faster Inference of Integer SWIN Transformer by Removing the GELU Activation
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.
AdCorDA: Classifier Refinement via Adversarial Correction and Domain Adaptation
This paper describes a simple yet effective technique for refining a pretrained classifier network.
Robustness to distribution shifts of compressed networks for edge devices
It is important to investigate the robustness of compressed networks in two types of data distribution shifts: domain shifts and adversarial perturbations.
BD-KD: Balancing the Divergences for Online Knowledge Distillation
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.
KronA: Parameter Efficient Tuning with Kronecker Adapter
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.
Predicting Visual Attention and Distraction During Visual Search Using Convolutional Neural Networks
Our second approach is object-based and predicts the distractor and target objects during visual search.
Target Features Affect Visual Search, A Study of Eye Fixations
Visual Search is referred to the task of finding a target object among a set of distracting objects in a visual display.
CES-KD: Curriculum-based Expert Selection for Guided Knowledge Distillation
Knowledge distillation (KD) is an effective tool for compressing deep classification models for edge devices.
Efficient Fine-Tuning of Compressed Language Models with Learners
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.
Clustered Saliency Prediction
We present a new method for image salience prediction, Clustered Saliency Prediction.
Efficient Fine-Tuning of BERT Models on the Edge
FAR reduces fine-tuning time on the DistilBERT model and CoLA dataset by 30%, and time spent on memory operations by 47%.
Consistency driven Sequential Transformers Attention Model for Partially Observable Scenes
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.
Standard Deviation-Based Quantization for Deep Neural Networks
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.
A Probabilistic Hard Attention Model For Sequentially Observed Scenes
A visual hard attention model actively selects and observes a sequence of subregions in an image to make a prediction.
Kronecker Decomposition for GPT Compression
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.
Visual Attention in Imaginative Agents
The next fixation is planned using uncertainty in the content of the imagined scenes.
HAD-Net: A Hierarchical Adversarial Knowledge Distillation Network for Improved Enhanced Tumour Segmentation Without Post-Contrast Images
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).
Achieving Explainability in a Visual Hard Attention Model through Content Prediction
Unlike in the deep convolution network, in hard attention it is explainable which regions of the image contributed to the prediction.
Grow-Push-Prune: aligning deep discriminants for effective structural network compression
We also show that our grown Inception nets (without hard-coded dimension alignment) clearly outperform residual nets of similar complexities.
Instance Segmentation based Semantic Matting for Compositing Applications
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.
Going From Image to Video Saliency: Augmenting Image Salience With Dynamic Attentional Push
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.
Task dependent Deep LDA pruning of neural networks
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.
WAYLA - Generating Images from Eye Movements
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.
Personalization of Saliency Estimation
The discriminator also has the observer label as an input, which contributes to the personalization ability of our approach.
Attentional Push: A Deep Convolutional Network for Augmenting Image Salience With Shared Attention Modeling in Social Scenes
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.
Efficient Gender Classification Using a Deep LDA-Pruned Net
Many real-time tasks, such as human-computer interaction, require fast and efficient facial gender classification.
Attentional Push: Augmenting Salience with Shared Attention Modeling
We present a novel visual attention tracking technique based on Shared Attention modeling.
