Related papers: A Strong Baseline for the VIPriors Data-Efficient …

Training an effective video action recognition model poses significant computational challenges, particularly under limited resource budgets. Current methods primarily aim to either reduce model size or utilize pre-trained models, limiting…

Verifying the authenticity of AI-generated images presents a growing challenge on social media platforms these days. While vision-language models (VLMs) like CLIP outdo in multimodal representation, their capacity for AI-generated image…

Data scarcity and noise are important issues in industrial applications of machine learning. However, it is often challenging to devise a scalable and generalized approach to address the fundamental distributional and semantic properties of…

In this paper, we tackle the new Cross-Domain Few-Shot Learning benchmark proposed by the CVPR 2020 Challenge. To this end, we build upon state-of-the-art methods in domain adaptation and few-shot learning to create a system that can be…

Since its release, ImageNet-1k dataset has become a gold standard for evaluating model performance. It has served as the foundation for numerous other datasets and training tasks in computer vision. As models have improved in accuracy,…

What can neural networks learn about the visual world when provided with only a single image as input? While any image obviously cannot contain the multitudes of all existing objects, scenes and lighting conditions - within the space of all…

The progress of composed image retrieval (CIR), a popular research direction in image retrieval, where a combined visual and textual query is used, is held back by the absence of high-quality training and evaluation data. We introduce a new…

Deep Learning systems have proven to be extremely successful for image recognition tasks for which significant amounts of training data is available, e.g., on the famous ImageNet dataset. We demonstrate that for robotics applications with…

The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably introduces significant variability in data quality, which…

Active learning focuses on choosing a subset of unlabeled data to be labeled. However, most such methods assume that a large subset of the data can be annotated. We are interested in low-budget active learning where only a small subset…

In this paper, we describe a feedforward artificial neural network trained on the ImageNet 2012 contest dataset [7] with the new method of [5] to an accuracy rate of 98.3% with a 99.69 Top-1 rate, and an average of 285.9 labels that are…

Conventional image classifiers are trained by randomly sampling mini-batches of images. To achieve state-of-the-art performance, practitioners use sophisticated data augmentation schemes to expand the amount of training data available for…

Visual representation learning hold great promise for robotics, but is severely hampered by the scarcity and homogeneity of robotics datasets. Recent works address this problem by pre-training visual representations on large-scale but…

Convolutional Neural Networks (CNNs) are prone to overfit small training datasets. We present a novel two-phase pipeline that leverages self-supervised learning and knowledge distillation to improve the generalization ability of CNN models…

The goal of few-shot learning is to recognize new visual concepts with just a few amount of labeled samples in each class. Recent effective metric-based few-shot approaches employ neural networks to learn a feature similarity comparison…

Utilizing massive web-scale datasets has led to unprecedented performance gains in machine learning models, but also imposes outlandish compute requirements for their training. In order to improve training and data efficiency, we here push…

Although deep learning approaches have stood out in recent years due to their state-of-the-art results, they continue to suffer from catastrophic forgetting, a dramatic decrease in overall performance when training with new classes added…

Fine-grained image classification is to recognize hundreds of subcategories in each basic-level category. Existing methods employ discriminative localization to find the key distinctions among subcategories. However, they generally have two…

We introduce N-ImageNet, a large-scale dataset targeted for robust, fine-grained object recognition with event cameras. The dataset is collected using programmable hardware in which an event camera consistently moves around a monitor…

Image compression emerges as a pivotal tool in the efficient handling and transmission of digital images. Its ability to substantially reduce file size not only facilitates enhanced data storage capacity but also potentially brings…