Search Results for author:
Found 52 papers, 16 papers with code
Curriculum Learning Effectively Improves Low Data VQA
In this paper, we propose curriculum-based learning (CL) regime to increase the accuracy of VQA models trained on small datasets.
BruSLeAttack: A Query-Efficient Score-Based Black-Box Sparse Adversarial Attack
We study the unique, less-well understood problem of generating sparse adversarial samples simply by observing the score-based replies to model queries.
Do Deep Neural Network Solutions Form a Star Domain?
This means that two independent solutions can be connected by a linear path with low loss, given one of them is appropriately permuted.
Premonition: Using Generative Models to Preempt Future Data Changes in Continual Learning
We show here that the combination of a large language model and an image generation model can similarly provide useful premonitions as to how a continual learning challenge might develop over time.
Neural Redshift: Random Networks are not Random Functions
Prevailing explanations are based on implicit biases of gradient descent (GD) but they cannot account for the capabilities of models from gradient-free methods nor the simplicity bias recently observed in untrained networks.
Unveiling Backbone Effects in CLIP: Exploring Representational Synergies and Variances
Contrastive Language-Image Pretraining (CLIP) stands out as a prominent method for image representation learning.
Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines
Large pre-trained models can dramatically reduce the amount of task-specific data required to solve a problem, but they often fail to capture domain-specific nuances out of the box.
SCONE-GAN: Semantic Contrastive learning-based Generative Adversarial Network for an end-to-end image translation
SCONE-GAN presents an end-to-end image translation, which is shown to be effective for learning to generate realistic and diverse scenery images.
Progressive Feature Adjustment for Semi-supervised Learning from Pretrained Models
As an effective way to alleviate the burden of data annotation, semi-supervised learning (SSL) provides an attractive solution due to its ability to leverage both labeled and unlabeled data to build a predictive model.
RanPAC: Random Projections and Pre-trained Models for Continual Learning
In this paper, we propose a concise and effective approach for CL with pre-trained models.
Semantic Role Labeling Guided Out-of-distribution Detection
Identifying unexpected domain-shifted instances in natural language processing is crucial in real-world applications.
Selective Mixup Helps with Distribution Shifts, But Not (Only) because of Mixup
We have found a new equivalence between two successful methods: selective mixup and resampling.
ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning
Finally, ProtoCon addresses the poor training signal in the initial phase of training (due to fewer confident predictions) by introducing an auxiliary self-supervised loss.
Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation
EBL can be used to improve the instance selection for a self-training task on the unlabelled target domain, and 2. alignment and normalizing energy scores can learn domain-invariant representations.
Stock Market Prediction via Deep Learning Techniques: A Survey
Existing surveys on stock market prediction often focus on traditional machine learning methods instead of deep learning methods.
Bayesian Learning with Information Gain Provably Bounds Risk for a Robust Adversarial Defense
We recognize the adversarial learning approach for approximating the multi-modal posterior distribution of a Bayesian model can lead to mode collapse; consequently, the model's achievements in robustness and performance are sub-optimal.
LAVA: Label-efficient Visual Learning and Adaptation
We present LAVA, a simple yet effective method for multi-domain visual transfer learning with limited data.
Predicting is not Understanding: Recognizing and Addressing Underspecification in Machine Learning
Underspecification refers to the existence of multiple models that are indistinguishable in their in-domain accuracy, even though they differ in other desirable properties such as out-of-distribution (OOD) performance.
EBMs vs. CL: Exploring Self-Supervised Visual Pretraining for Visual Question Answering
In a simple setting similar to CLEVR, we find that CL representations also improve systematic generalization, and even match the performance of representations from a larger, supervised, ImageNet-pretrained model.
Astock: A New Dataset and Automated Stock Trading based on Stock-specific News Analyzing Model
In addition, we propose a self-supervised learning strategy based on SRLP to enhance the out-of-distribution generalization performance of our system.
Ranked #1 on
Stock Price Prediction
on Astock
Progressive Class Semantic Matching for Semi-supervised Text Classification
Semi-supervised learning is a promising way to reduce the annotation cost for text-classification.
Active Learning by Feature Mixing
We identify unlabelled instances with sufficiently-distinct features by seeking inconsistencies in predictions resulting from interventions on their representations.
Query Efficient Decision Based Sparse Attacks Against Black-Box Deep Learning Models
The ability to extract information from solely the output of a machine learning model to craft adversarial perturbations to black-box models is a practical threat against real-world systems, such as autonomous cars or machine learning models exposed as a service (MLaaS).
RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit
In our study, we first deep dive into recent state-of-the-art decision-based attacks in ICLR and SP to highlight the costly nature of discovering low distortion adversarial employing gradient estimation methods.
TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems
Now, an adversary can arm themselves with a patch that is naturalistic, less malicious-looking, physically realizable, highly effective achieving high attack success rates, and universal.
iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients
A key challenge to the scalability and quality of the learned architectures is the need for differentiating through the inner-loop optimisation.
Ranked #22 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
Evading the Simplicity Bias: Training a Diverse Set of Models Discovers Solutions with Superior OOD Generalization
The method - the first to evade the simplicity bias - highlights the need for a better understanding and control of inductive biases in deep learning.
All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training
We train two classifiers with two different views of the class labels: one classifier uses the one-hot view of the labels and disregards any potential similarity among the classes, while the other uses a distributed view of the labels and groups potentially similar classes together.
Learning for Visual Navigation by Imagining the Success
ForeSIT is trained to imagine the recurrent latent representation of a future state that leads to success, e. g. either a sub-goal state that is important to reach before the target, or the goal state itself.
Unshuffling Data for Improved Generalization in Visual Question Answering
subsets treated as multiple training environments can guide the learning of models with better out-of-distribution generalization.
Counterfactual Vision-and-Language Navigation: Unravelling the Unseen
The task of vision-and-language navigation (VLN) requires an agent to follow text instructions to find its way through simulated household environments.
Counterfactual Vision and Language Learning
It is particularly remarkable that this success has been achieved on the basis of comparatively small datasets, given the scale of the problem.
On the Value of Out-of-Distribution Testing: An Example of Goodhart's Law
Out-of-distribution (OOD) testing is increasingly popular for evaluating a machine learning system's ability to generalize beyond the biases of a training set.
Optimistic Agent: Accurate Graph-Based Value Estimation for More Successful Visual Navigation
Through empirical studies, we show that our agent, dubbed as the optimistic agent, has a more realistic estimate of the state value during a navigation episode which leads to a higher success rate.
Hybrid Neuro-Evolutionary Method for Predicting Wind Turbine Power Output
Reliable wind turbine power prediction is imperative to the planning, scheduling and control of wind energy farms for stable power production.
Unshuffling Data for Improved Generalization
subsets treated as multiple training environments can guide the learning of models with better out-of-distribution generalization.
An Evolutionary Deep Learning Method for Short-term Wind Speed Prediction: A Case Study of the Lillgrund Offshore Wind Farm
Accurate short-term wind speed forecasting is essential for large-scale integration of wind power generation.
On Incorporating Semantic Prior Knowledge in Deep Learning Through Embedding-Space Constraints
We also show that incorporating this type of prior knowledge with our method brings consistent improvements, independently from the amount of supervised data used.
On Incorporating Semantic Prior Knowlegde in Deep Learning Through Embedding-Space Constraints
We also show that incorporating this type of prior knowledge with our method brings consistent improvements, independently from the amount of supervised data used.
Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network Systems
Notably, in contrast to existing approaches, our approach removes the need for ground-truth labelled data or anomaly detection methods for Trojan detection or retraining a model or prior knowledge of an attack.
Cryptography and Security
Adaptive Neuro-Surrogate-Based Optimisation Method for Wave Energy Converters Placement Optimisation
The installed amount of renewable energy has expanded massively in recent years.
Deep Single Image Deraining Via Estimating Transmission and Atmospheric Light in rainy Scenes
Instead of using the estimated atmospheric light directly to learn a network to calculate transmission, we utilize it as ground truth and design a simple but novel triangle-shaped network structure to learn atmospheric light for every rainy image, then fine-tune the network to obtain a better estimation of atmospheric light during the training of transmission network.
Follow the Attention: Combining Partial Pose and Object Motion for Fine-Grained Action Detection
We empirically show the capability of our approach by achieving state-of-the-art results on MERL shopping dataset.
Show, Price and Negotiate: A Negotiator with Online Value Look-Ahead
Negotiation, as an essential and complicated aspect of online shopping, is still challenging for an intelligent agent.
Reinforcement Learning with Attention that Works: A Self-Supervised Approach
Attention models have had a significant positive impact on deep learning across a range of tasks.
What's to know? Uncertainty as a Guide to Asking Goal-oriented Questions
We propose a solution to this problem based on a Bayesian model of the uncertainty in the implicit model maintained by the visual dialogue agent, and in the function used to select an appropriate output.
Gold Seeker: Information Gain from Policy Distributions for Goal-oriented Vision-and-Langauge Reasoning
For each potential action a distribution of the expected outcomes is calculated, and the value of the potential information gain assessed.
Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables
Automatic recognition of human activities from time-series sensor data (referred to as HAR) is a growing area of research in ubiquitous computing.
3D Hand Pose Estimation using Simulation and Partial-Supervision with a Shared Latent Space
In this paper, we propose a novel method that seeks to predict the 3d position of the hand using both synthetic and partially-labeled real data.
Deep Lipschitz networks and Dudley GANs
To facilitate this, we develop both theoretical and practical building blocks, using which one can construct different neural networks using a large range of metrics, as well as ensure Lipschitz condition and sufficient capacity of the networks.
DeepSetNet: Predicting Sets with Deep Neural Networks
This paper addresses the task of set prediction using deep learning.
Infinite Variational Autoencoder for Semi-Supervised Learning
This paper presents an infinite variational autoencoder (VAE) whose capacity adapts to suit the input data.
