Search Results for author:
Found 58 papers, 35 papers with code
IntentGPT: Few-shot Intent Discovery with Large Language Models
IntentGPT comprises an \textit{In-Context Prompt Generator}, which generates informative prompts for In-Context Learning, an \textit{Intent Predictor} for classifying and discovering user intents from utterances, and a \textit{Semantic Few-Shot Sampler} that selects relevant few-shot examples and a set of known intents to be injected into the prompt.
InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
We also compare the performance of open- and closed-source LLMs and various evaluation strategies.
RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
We run a large-scale benchmark comprising several state-of-the-art LLMs to uncover differences in performance across models of various types and sizes in a context-conditional language modeling setting.
WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?
We study the use of large language model-based agents for interacting with software via web browsers.
Capture the Flag: Uncovering Data Insights with Large Language Models
The extraction of a small number of relevant insights from vast amounts of data is a crucial component of data-driven decision-making.
StarVector: Generating Scalable Vector Graphics Code from Images and Text
It performs image vectorization by understanding image semantics and using SVG primitives for compact, precise outputs.
OC-NMN: Object-centric Compositional Neural Module Network for Generative Visual Analogical Reasoning
A key aspect of human intelligence is the ability to imagine -- composing learned concepts in novel ways -- to make sense of new scenarios.
Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection
Our findings reveal that while these methods excel in detecting unknown classes, their performance is inconsistent when encountering other types of distribution shifts.
GEO-Bench: Toward Foundation Models for Earth Monitoring
Recent progress in self-supervision has shown that pre-training large neural networks on vast amounts of unsupervised data can lead to substantial increases in generalization to downstream tasks.
Improving Generalization in Task-oriented Dialogues with Workflows and Action Plans
We perform extensive experiments on the Action-Based Conversations Dataset (ABCD) with T5-small, base and large models, and show that such models: a) are able to more readily generalize to unseen workflows by following the provided plan, and b) are able to generalize to executing unseen actions if they are provided in the plan.
FigGen: Text to Scientific Figure Generation
The generative modeling landscape has experienced tremendous growth in recent years, particularly in generating natural images and art.
Language Decision Transformers with Exponential Tilt for Interactive Text Environments
Text-based game environments are challenging because agents must deal with long sequences of text, execute compositional actions using text and learn from sparse rewards.
3rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understanding
Continual Learning, also known as Lifelong or Incremental Learning, has recently gained renewed interest among the Artificial Intelligence research community.
Exploring validation metrics for offline model-based optimisation with diffusion models
Measuring the mean reward of generated candidates over this approximation is one such `validation metric', whereas we are interested in a more fundamental question which is finding which validation metrics correlate the most with the ground truth.
Flaky Performances when Pretraining on Relational Databases
We explore the downstream task performances for graph neural network (GNN) self-supervised learning (SSL) methods trained on subgraphs extracted from relational databases (RDBs).
Implicit Offline Reinforcement Learning via Supervised Learning
Despite the benefits of using implicit models to learn robotic skills via BC, offline RL via Supervised Learning algorithms have been limited to explicit models.
OCR-VQGAN: Taming Text-within-Image Generation
To alleviate this problem, we present OCR-VQGAN, an image encoder, and decoder that leverages OCR pre-trained features to optimize a text perceptual loss, encouraging the architecture to preserve high-fidelity text and diagram structure.
Constraining Representations Yields Models That Know What They Don't Know
In the add-on case, the original neural network's inference head is completely unaffected (so its accuracy remains the same) but we now have the option to use TAC's own confidence and prediction when determining which course of action to take in an hypothetical production workflow.
Workflow Discovery from Dialogues in the Low Data Regime
We propose and evaluate an approach that conditions models on the set of possible actions, and we show that using this strategy, we can improve WD performance.
Ranked #1 on
Workflow Discovery
on ABCD
Data Augmentation for Intent Classification with Off-the-shelf Large Language Models
Data augmentation is a widely employed technique to alleviate the problem of data scarcity.
Overcoming challenges in leveraging GANs for few-shot data augmentation
In this paper, we explore the use of GAN-based few-shot data augmentation as a method to improve few-shot classification performance.
Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark
Recent progress in self-supervision shows that pre-training large neural networks on vast amounts of unsupervised data can lead to impressive increases in generalisation for downstream tasks.
Multi-label Iterated Learning for Image Classification with Label Ambiguity
We also show that MILe is effective reducing label noise, achieving state-of-the-art performance on real-world large-scale noisy data such as WebVision.
Ranked #6 on
Image Classification
on WebVision-1000
A Survey of Self-Supervised and Few-Shot Object Detection
Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image.
A Deep Learning Localization Method for Measuring Abdominal Muscle Dimensions in Ultrasound Images
US images can be used to measure abdominal muscles dimensions for the diagnosis and creation of customized treatment plans for patients with Low Back Pain (LBP), however, they are difficult to interpret.
Overcoming Label Ambiguity with Multi-label Iterated Learning
This ambiguity biases models towards a single prediction, which could result in the suppression of classes that tend to co-occur in the data.
SSR: Semi-supervised Soft Rasterizer for single-view 2D to 3D Reconstruction
In order to obtain the viewpoints for these unlabeled images, we propose to use a Siamese network that takes two images as input and outputs whether they correspond to the same viewpoint.
Touch-based Curiosity for Sparse-Reward Tasks
Robots in many real-world settings have access to force/torque sensors in their gripper and tactile sensing is often necessary in tasks that involve contact-rich motion.
Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data
Transfer learning approaches can reduce the data requirements of deep learning algorithms.
Ranked #4 on
Change Detection
on OSCD - 13ch
(using extra training data)
Beyond Trivial Counterfactual Explanations with Diverse Valuable Explanations
Explainability for machine learning models has gained considerable attention within the research community given the importance of deploying more reliable machine-learning systems.
Knowledge Hypergraph Embedding Meets Relational Algebra
Embedding-based methods for reasoning in knowledge hypergraphs learn a representation for each entity and relation.
Beyond Trivial Counterfactual Generations with Diverse Valuable Explanations
In computer vision applications, most methods explain models by displaying the regions in the input image that they focus on for their prediction, but it is difficult to improve models based on these explanations since they do not indicate why the model fail.
Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery
Cattle farming is responsible for 8. 8\% of greenhouse gas emissions worldwide.
Affinity LCFCN: Learning to Segment Fish with Weak Supervision
Leading automatic approaches rely on fully-supervised segmentation models to acquire these measurements but these require collecting per-pixel labels -- also time consuming and laborious: i. e., it can take up to two minutes per fish to generate accurate segmentation labels, almost always requiring at least some manual intervention.
CVPR 2020 Continual Learning in Computer Vision Competition: Approaches, Results, Current Challenges and Future Directions
In the last few years, we have witnessed a renewed and fast-growing interest in continual learning with deep neural networks with the shared objective of making current AI systems more adaptive, efficient and autonomous.
A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis
The dataset consists of approximately 40 thousand images collected underwater from 20 \green{habitats in the} marine-environments of tropical Australia.
A Weakly Supervised Region-Based Active Learning Method for COVID-19 Segmentation in CT Images
We address this challenge introducing a scalable, fast, and accurate active learning system that accelerates the labeling of CT scan images.
A Weakly Supervised Consistency-based Learning Method for COVID-19 Segmentation in CT Images
Thus, we propose a consistency-based (CB) loss function that encourages the output predictions to be consistent with spatial transformations of the input images.
LOOC: Localize Overlapping Objects with Count Supervision
For localization, LOOC achieves a strong new baseline in the novel problem setup where only count supervision is available.
Learning Data Augmentation with Online Bilevel Optimization for Image Classification
Data augmentation is a key practice in machine learning for improving generalization performance.
Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images using a View-based Representation
We propose Pix2Shape, an approach to solve this problem with four components: (i) an encoder that infers the latent 3D representation from an image, (ii) a decoder that generates an explicit 2. 5D surfel-based reconstruction of a scene from the latent code (iii) a differentiable renderer that synthesizes a 2D image from the surfel representation, and (iv) a critic network trained to discriminate between images generated by the decoder-renderer and those from a training distribution.
Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning
We propose Continual-MAML, an online extension of the popular MAML algorithm as a strong baseline for this scenario.
Slanted Stixels: A way to represent steep streets
This work presents and evaluates a novel compact scene representation based on Stixels that infers geometric and semantic information.
Adversarial Learning of General Transformations for Data Augmentation
Data augmentation (DA) is fundamental against overfitting in large convolutional neural networks, especially with a limited training dataset.
Fourier-CPPNs for Image Synthesis
Compositional Pattern Producing Networks (CPPNs) are differentiable networks that independently map (x, y) pixel coordinates to (r, g, b) colour values.
Class-Based Styling: Real-time Localized Style Transfer with Semantic Segmentation
We propose a Class-Based Styling method (CBS) that can map different styles for different object classes in real-time.
Where are the Masks: Instance Segmentation with Image-level Supervision
A major obstacle in instance segmentation is that existing methods often need many per-pixel labels in order to be effective.
Ranked #9 on
Image-level Supervised Instance Segmentation
on PASCAL VOC 2012 val
(using extra training data)
Image-level Supervised Instance Segmentation
Semantic Segmentation
Instance Segmentation with Point Supervision
Instance segmentation methods often require costly per-pixel labels.
Knowledge Hypergraphs: Prediction Beyond Binary Relations
Knowledge graphs store facts using relations between two entities.
Pix2Scene: Learning Implicit 3D Representations from Images
Modelling 3D scenes from 2D images is a long-standing problem in computer vision with implications in, e. g., simulation and robotics.
Context-Aware Visual Compatibility Prediction
How do we determine whether two or more clothing items are compatible or visually appealing?
Ranked #1 on
Slot Filling
on Polyvore
Where are the Blobs: Counting by Localization with Point Supervision
However, we propose a detection-based method that does not need to estimate the size and shape of the objects and that outperforms regression-based methods.
Ranked #1 on
Object Counting
on Pascal VOC 2007 count-test
From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example
However, since the models learned with virtual data must operate in the real world, we still need to perform domain adaptation (DA).
The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation
State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs).
Ranked #12 on
Semantic Segmentation
on CamVid
PixelVAE: A Latent Variable Model for Natural Images
Natural image modeling is a landmark challenge of unsupervised learning.
Node-Adapt, Path-Adapt and Tree-Adapt:Model-Transfer Domain Adaptation for Random Forest
Random Forest (RF) is a successful paradigm for learning classifiers due to its ability to learn from large feature spaces and seamlessly integrate multi-class classification, as well as the achieved accuracy and processing efficiency.
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
In order to answer this question we have generated a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations.
Hierarchical Adaptive Structural SVM for Domain Adaptation
In both cases, we show how HA-SSVM is effective in increasing the detection/recognition accuracy with respect to adaptation strategies that ignore the structure of the target data.
