Related papers: Core Risk Minimization using Salient ImageNet
Camera model identification (CMI) has gained significant importance in image forensics as digitally altered images are becoming increasingly commonplace. In this paper, a novel convolutional neural network (CNN) architecture is proposed for…
We propose techniques to incorporate coarse taxonomic labels to train image classifiers in fine-grained domains. Such labels can often be obtained with a smaller effort for fine-grained domains such as the natural world where categories are…
In image Super-Resolution (SR), relying on large datasets for training is a double-edged sword. While offering rich training material, they also demand substantial computational and storage resources. In this work, we analyze dataset…
A key inefficiency in diffusion training occurs when a randomly initialized network, lacking visual priors, encounters gradients from the full complexity spectrum--most of which it lacks the capacity to resolve. We propose Data Warmup, a…
Spurious correlations pose a major challenge for robust machine learning. Models trained with empirical risk minimization (ERM) may learn to rely on correlations between class labels and spurious attributes, leading to poor performance on…
Designing adversarially robust models from a data-centric perspective requires understanding which input samples are most crucial for learning resilient features. While coreset selection provides a mechanism for efficient training on data…
To improve the efficiency and sustainability of learning deep models, we propose CREST, the first scalable framework with rigorous theoretical guarantees to identify the most valuable examples for training non-convex models, particularly…
Deep learning in general domains has constantly been extended to domain-specific tasks requiring the recognition of fine-grained characteristics. However, real-world applications for fine-grained tasks suffer from two challenges: a high…
We tackle a novel few-shot learning challenge, which we call few-shot semantic edge detection, aiming to localize crisp boundaries of novel categories using only a few labeled samples. We also present a Class-Agnostic Few-shot Edge…
Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet,…
We present a simple but effective method to measure and mitigate model biases caused by reliance on spurious cues. Instead of requiring costly changes to one's data or model training, our method better utilizes the data one already has by…
Spurious correlations that degrade model generalization or lead the model to be right for the wrong reasons are one of the main robustness concerns for real-world deployments. However, mitigating these correlations during pre-training for…
Deep neural networks have exhibited remarkable performance in various domains. However, the reliance of these models on spurious features has raised concerns about their reliability. A promising solution to this problem is last-layer…
This work investigates the well-known problem of morphing attacks, which has drawn considerable attention in the biometrics community. Morphed images have exposed face recognition systems' susceptibility to false acceptance, resulting in…
A central goal of machine learning is to learn robust representations that capture the causal relationship between inputs features and output labels. However, minimizing empirical risk over finite or biased datasets often results in models…
Recent advances in learning or identification of nonlinear dynamics focus on learning a suitable model within a pre-specified model class. However, a key difficulty that remains is the choice of the model class from which the dynamics will…
Much of the recent efforts on salient object detection (SOD) have been devoted to producing accurate saliency maps without being aware of their instance labels. To this end, we propose a new pipeline for end-to-end salient instance…
Depth images and thermal images contain the spatial geometry information and surface temperature information, which can act as complementary information for the RGB modality. However, the quality of the depth and thermal images is often…
Empirical risk minimization (ERM) is ubiquitous in machine learning and underlies most supervised learning methods. While there has been a large body of work on algorithms for various ERM problems, the exact computational complexity of ERM…
Few-shot learning (FSL) has recently been extensively utilized to overcome the scarcity of training data in domain-specific visual recognition. In real-world scenarios, environmental factors such as complex backgrounds, varying lighting…