Related papers: Improving Baselines in the Wild

Large Language Models (LLMs) are of great interest in vulnerability detection and repair. The effectiveness of these models hinges on the quality of the datasets used for both training and evaluation. Our investigation reveals that a number…

Wildlife monitoring is crucial to nature conservation and has been done by manual observations from motion-triggered camera traps deployed in the field. Widespread adoption of such in-situ sensors has resulted in unprecedented data volumes…

Model-based reinforcement learning promises strong sample efficiency but often underperforms in practice due to compounding model error, unimodal world models that average over multi-modal dynamics, and overconfident predictions that bias…

With the development of deep learning, Deep Metric Learning (DML) has achieved great improvements in face recognition. Specifically, the widely used softmax loss in the training process often bring large intra-class variations, and feature…

Image-level regression is an important task in Earth observation, where visual domain and label shifts are a core challenge hampering generalization. However, cross-domain regression within remote sensing data remains understudied due to…

While pretraining on large-scale image-text data from the Web has facilitated rapid progress on many vision-and-language (V&L) tasks, recent work has demonstrated that pretrained models lack "fine-grained" understanding, such as the ability…

Since its beginning visual recognition research has tried to capture the huge variability of the visual world in several image collections. The number of available datasets is still progressively growing together with the amount of samples…

Modern incremental learning for semantic segmentation methods usually learn new categories based on dense annotations. Although achieve promising results, pixel-by-pixel labeling is costly and time-consuming. Weakly incremental learning for…

Lightweight vision classification models such as MobileNet, ShuffleNet, and EfficientNet are increasingly deployed in mobile and embedded systems, yet their performance has been predominantly benchmarked on ImageNet. This raises critical…

Recent progress on few-shot learning largely relies on annotated data for meta-learning: base classes sampled from the same domain as the novel classes. However, in many applications, collecting data for meta-learning is infeasible or…

Multimodal models often over-rely on dominant modalities, failing to achieve optimal performance. While prior work focuses on modifying training objectives or optimization procedures, data-centric solutions remain underexplored. We propose…

Fine-grained bird species identification in the wild is frequently unanswerable from a single image: key cues may be non-visual (e.g. vocalization), or obscured due to occlusion, camera angle, or low resolution. Yet today's multimodal…

The explosion of IoT sensors in industrial, consumer and remote sensing use cases has come with unprecedented demand for computing infrastructure to transmit and to analyze petabytes of data. Concurrently, the world is slowly shifting its…

Mislabeled samples are ubiquitous in real-world datasets as rule-based or expert labeling is usually based on incorrect assumptions or subject to biased opinions. Neural networks can "memorize" these mislabeled samples and, as a result,…

Image classification with small datasets has been an active research area in the recent past. However, as research in this scope is still in its infancy, two key ingredients are missing for ensuring reliable and truthful progress: a…

Although multimodal fusion has made significant progress, its advancement is severely hindered by the lack of adequate evaluation benchmarks. Current fusion methods are typically evaluated on a small selection of public datasets, a limited…

Foundation models (FMs), i.e., models trained on a vast amount of typically unlabeled data, have become popular and available recently for the domain of histopathology. The key idea is to extract semantically rich vectors from any input…

Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples. While significant progress has been made, the growing complexity of network designs, meta-learning algorithms, and…

The role of soft biometrics to enhance person recognition systems in unconstrained scenarios has not been extensively studied. Here, we explore the utility of the following modalities: gender, ethnicity, age, glasses, beard, and moustache.…

The study of model bias and variance with respect to decision boundaries is critically important in supervised classification. There is generally a tradeoff between the two, as fine-tuning of the decision boundary of a classification model…