Meta Omnium benchmarks few-shot learning across diverse vision tasks.
problem Evaluating generalization of few-shot learning across multiple vision tasks.
method Introduction of Meta Omnium dataset and evaluation of meta-learning algorithms.
result Meta-learning algorithms can generalize across diverse vision tasks.
An important goal of computer vision is to build systems that learn visual representations over time that can be applied to many tasks. In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task learning. In particular…
Computer vision models are unstable due to task symmetries and labelling issues.
problem Instability of computer vision models in classification tasks.
method Analysis of symmetries, categorical nature, and labelling issues.
result Instability is a necessary result of current computer vision formulation.
Robust CLIP improves vision models' resistance to attacks.
problem Vulnerability of vision models to adversarial attacks.
method Unsupervised adversarial fine-tuning of CLIP.
result Robust CLIP prevents stealth attacks on vision models.
Detects anomalies in autonomous mobile robots using vision.
problem Anomaly detection for autonomous mobile robots.
method Unsupervised deep learning methods and a novel dataset.
result State-of-the-art approach tested on a new dataset.
Real-time uncertainty estimation for computer vision tasks.
problem Real-time inference of uncertainty in deep learning models.
method Uncertainty-Aware Distribution Distillation method for fast inference.
result Significantly reduced inference time with improved uncertainty and predictive performance.
Quantum hybrid vision transformers improve event classification in high energy physics.
problem Excessive computational resources for training and deploying vision transformer models.
method Constructed quantum hybrid vision transformers for high energy physics event classification.
result Quantum hybrid models achieve comparable performance to classical models with fewer parameters.
Plex improves model reliability across vision and language tasks.
problem Improving model reliability in diverse decision-making tasks involving uncertainty and adaptation.
method Developed ViT-Plex and T5-Plex pretrained model extensions to evaluate and improve reliability across 40 datasets.
result Plex greatly improves state-of-the-art across reliability tasks, simplifying evaluation and performance.
The recent breakthroughs in computer vision have benefited from the availability of large representative datasets (e.g. ImageNet and COCO) for training. Yet, robotic vision poses unique challenges for applying visual algorithms developed from these standard computer vision datasets due to their implicit assumption over…
Develops methods for training models with few annotations in computer vision tasks.
problem Training models with limited labeled data in computer vision.
method Theoretical, algorithmic, and experimental contributions for Meta-Learning and Semi-Supervised Learning.
result Improves Contrastive Learning and proposes a semi-supervised method for transformer-based object detectors.
ADAPT improves robustness of Vision Transformers without full model fine-tuning.
problem Vulnerability of Vision Transformers to adversarial attacks.
method Parameter-efficient prompt tuning with ADAPT framework for adaptive adversarial training.
result ADAPT achieves robust accuracy of ~40% w.r.t. SOTA methods using only ~1% of the parameters.
GSA-Nets apply group equivariance to self-attention for vision tasks.
problem Improving self-attention networks for vision tasks.
method Define group-equivariant positional encodings.
result GSA-Nets outperform non-equivariant self-attention networks on vision benchmarks.
The democratization of machine learning (ML) has led to ML-based machine vision systems for autonomous driving, traffic monitoring, and video surveillance. However, true democratization cannot be achieved without greatly simplifying the process of collecting groundtruth for training and testing these systems. This grou…
ViLT is a faster vision-and-language model without convolution or region supervision.
problem Efficiency and expressive power limitations in current VLP models.
method A convolution-free Vision-and-Language Transformer (ViLT) that processes visual inputs similarly to textual inputs.
result ViLT is up to tens of times faster with competitive or better performance.
Proposes deep collective learning to learn inputs and weights together in neural networks.
problem The need to optimize inputs alongside weights in deep neural networks.
method Introduces deep collective learning to learn inputs and weights jointly, using lookup tables.
result Demonstrates advantages and promise of Lookup-VNets and deep collective learning.
This paper improves ensemble learning for vision tasks by encouraging diversity in predictions.
problem Generating effective ensembles of neural networks for multi-modal data.
method Explicitly optimize a diversity inducing adversarial loss for learning stochastic latent variables.
result Significant improvements in classification accuracy and out-of-distribution detection compared to baselines.
Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence. Ideally, these tasks should test a plethora of capabilities that integrate computer vision, reasoning, and natural language understanding. However, rather than behaving as visual Turing t…
We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via language to find objects in photorealistic indoor environments. The task emulates a real-world scenario in that (a) the requester may not know how to navigate to …
Study proposes a statistical test for Vision Transformer's attention mechanisms.
problem ViT's attention mechanisms may focus on irrelevant regions, leading to unreliable evidence.
method Selective inference framework to quantify statistical significance of attentions as p-values.
result Proposed method enables reliable quantification of false positive detection probability of attentions.
This paper tackles shape denoising in computer vision and medical imaging.
problem Handling shapes with missing pieces or outliers in shape modeling.
method Introduces six types of noise and an objective measure for shape denoising.
result Evaluates seven shape denoising methods, six of which are based on deep learning.
As the range of tasks performed by a general vision system expands, executing multiple tasks accurately and efficiently in a single network has become an important and still open problem. Recent computer vision approaches address this problem by branching networks, or by a channel-wise modulation of the network feature…
Vision Transformers show different internal representations compared to CNNs.
problem Understanding how Vision Transformers solve image classification tasks.
method Comparative analysis of ViT and CNN architectures on image classification benchmarks.
result ViT has more uniform representations across all layers, while CNNs have more varied representations.
GTA improves transformer-based NVS models by encoding geometric structure.
problem Suboptimal positional encoding for 3D vision tasks.
method Geometry-aware attention mechanism encoding geometric structure of tokens.
result GTA improves learning efficiency and performance of NVS models.
We present a method for fast training of vision based control policies on real robots. The key idea behind our method is to perform multi-task Reinforcement Learning with auxiliary tasks that differ not only in the reward to be optimized but also in the state-space in which they operate. In particular, we allow auxilia…
While frame-independent predictions with deep neural networks have become the prominent solutions to many computer vision tasks, the potential benefits of utilizing correlations between frames have received less attention. Even though probabilistic machine learning provides the ability to encode correlation as prior kn…
Weakly-supervised RL identifies meaningful tasks, improving performance in complex environments.
problem Learning to efficiently explore and distinguish between meaningful and irrelevant tasks.
method Weak supervision to automatically disentangle meaningful tasks from a large space of nonsensical tasks.
result The learned subspace of meaningful tasks leads to substantial performance gains, especially in complex environments.
AI models aligned with human vision perform well on few data tasks.
problem Few-shot learning performance with limited data.
method Information-theoretic analysis and empirical testing of 491 models.
result Highly aligned models show better robustness to attacks and domain shifts.
From a simplified analysis of adaptive methods, we derive AvaGrad, a new optimizer which outperforms SGD on vision tasks when its adaptability is properly tuned. We observe that the power of our method is partially explained by a decoupling of learning rate and adaptability, greatly simplifying hyperparameter search. I…
Paper proposes privacy-preserving learning for images, making them imperceptible to humans but recognizable by machines.
problem Conflict between developing AI systems and protecting sensitive training data.
method Encryption strategies (random shuffling and sub-patch mixing) followed by minimal adaptation to vision transformer.
result Achieves comparable accuracy to competitive methods while ensuring human-imperceptibility of encrypted images.
Mobile V-MoEs scale down ViTs for resource-constrained vision tasks.
problem Scaling down Vision Transformers for resource-constrained applications.
method Sparse Mixture-of-Experts (MoEs) applied to entire images, with a stable training procedure.
result Mobile V-MoEs achieve better performance-efficiency trade-offs than dense ViTs.
We introduce a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection. It achieves near-original model performance on common computer vision architectures and tasks. 8-bit fixed-point quantization is essential for efficient inference on modern deep learning …
Square loss performs comparably or better than cross-entropy in neural architectures for various tasks.
problem The superiority of cross-entropy loss over square loss in classification tasks is debated.
method Comparison of several neural architectures on NLP, ASR, and computer vision datasets using both loss functions.
result Square loss often produces better results in the majority of tasks, especially in NLP and ASR.
Proposes a method to balance tasks in multitask learning with a single gradient step update.
problem Balancing tasks in multitask learning to avoid imbalance.
method Gradient-based meta-learning to balance tasks at the gradient level, training shared and task-specific layers separately.
result Achieves state-of-the-art performance on various multitask computer vision problems.
New framework tackles DG under posterior drift, where optimal classifier varies by domain.
problem Generalizing from multiple domains with varying optimal classifiers.
method Decision-theoretic framework for DG under posterior drift.
result Optimal classifier can vary significantly across domains, challenging existing DG approaches.
Imitation learning allows agents to learn complex behaviors from demonstrations. However, learning a complex vision-based task may require an impractical number of demonstrations. Meta-imitation learning is a promising approach towards enabling agents to learn a new task from one or a few demonstrations by leveraging e…
Task-agnostic data augmentation shows little benefit for pretrained transformers.
problem Evaluating the effectiveness of task-agnostic data augmentation on pretrained transformers.
method Conducted a systematic examination of two data augmentation techniques (Easy Data Augmentation and Back-Translation) across 5 tasks, 6 datasets, and 3 pretrained transformer models.
result Data augmentation techniques previously effective for non-pretrained models fail to consistently improve performance for pretrained transformers, even with limited training data.
Attention networks show promise for both vision and language tasks, by emphasizing relationships between constituent elements through weighting functions. Such elements could be regions in an image output by a region proposal network, or words in a sentence, represented by word embedding. Thus far the learning of atten…
VALAN is a lightweight and scalable software framework for deep reinforcement learning based on the SEED RL architecture. The framework facilitates the development and evaluation of embodied agents for solving grounded language understanding tasks, such as Vision-and-Language Navigation and Vision-and-Dialog Navigation…
Visual object detection is a computer vision-based artificial intelligence (AI) technique which has many practical applications (e.g., fire hazard monitoring). However, due to privacy concerns and the high cost of transmitting video data, it is highly challenging to build object detection models on centrally stored lar…
Proposes hinge-Wasserstein to improve uncertainty estimation in regression tasks.
problem Estimating multimodal aleatoric uncertainty in regression tasks from images.
method Regression-by-classification paradigm with hinge-Wasserstein loss.
result Hinge-Wasserstein loss improves uncertainty estimation on challenging tasks.
Paper introduces a multi-stage influence function to track model predictions.
problem Improving natural language processing and computer vision performance.
method Develops a multi-stage influence function to track predictions from finetuned models back to pretraining data.
result Identifies pretraining examples contributing most to finetuning task predictions.
B-cos transformers explain Vision Transformers' decisions.
problem Lack of holistic explanations for transformer outputs.
method Formulate each component as dynamic linear, allowing a single linear transform for summarization.
result Bcos-ViTs are highly interpretable and competitive on ImageNet.
Novel regularization for Vision Transformers improves model generalization and sparsity.
problem Improving generalization and sparsity in Vision Transformers.
method Likelihood-guided variational Ising-based regularization.
result Improved generalization and sparsity in Vision Transformers.
Manipulation tasks such as preparing a meal or assembling furniture remain highly challenging for robotics and vision. Traditional task and motion planning (TAMP) methods can solve complex tasks but require full state observability and are not adapted to dynamic scene changes. Recent learning methods can operate direct…
This paper analyzes shallow ViTs, providing sample complexity and SGD behavior insights.
problem Theoretical understanding of shallow ViTs, especially their sample complexity and SGD behavior.
method Data model with label-relevant and label-irrelevant tokens, theoretical analysis of shallow ViT training.
result Characterization of sample complexity for zero generalization error in shallow ViTs.
Fisheye cameras are commonly employed for obtaining a large field of view in surveillance, augmented reality and in particular automotive applications. In spite of their prevalence, there are few public datasets for detailed evaluation of computer vision algorithms on fisheye images. We release the first extensive fish…
Improved transfer learning with expert models, reducing compute and speeding up performance.
problem Improving sample efficiency and reducing computational requirements for new tasks.
method Training a diverse set of experts using existing label structures and performance proxies to select the relevant expert for each target task.
result Significant speed-up of 2-3 orders of magnitude compared to competing approaches.
Mimetic initialization improves Transformer training on small datasets.
problem Difficulty in training Transformers on small datasets.
method Initialize self-attention layers to look like pre-trained models.
result Vanilla Transformers trained with mimetic initialization achieve higher accuracy.