Search Results for author:
Found 14 papers, 9 papers with code
DD-Ranking: Rethinking the Evaluation of Dataset Distillation
In recent years, dataset distillation has provided a reliable solution for data compression, where models trained on the resulting smaller synthetic datasets achieve performance comparable to those trained on the original datasets.
ICONS: Influence Consensus for Vision-Language Data Selection
In this work, we introduce ICONS, a gradient-driven Influence CONsensus approach for vision-language data Selection that selects a compact training dataset for efficient multi-task training.
SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?
Therefore, we propose SWE-bench Multimodal (SWE-bench M), to evaluate systems on their ability to fix bugs in visual, user-facing JavaScript software.
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
Compositionality is a critical capability in Text-to-Image (T2I) models, as it reflects their ability to understand and combine multiple concepts from text descriptions.
CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
All models lag far behind human performance of 80. 5%, underscoring weaknesses in the chart understanding capabilities of existing MLLMs.
Vision-Language Dataset Distillation
In this work, we design the first vision-language dataset distillation method, building on the idea of trajectory matching.
Pix2Map: Cross-modal Retrieval for Inferring Street Maps from Images
Moreover, we show that our retrieved maps can be used to update or expand existing maps and even show proof-of-concept results for visual localization and image retrieval from spatial graphs.
Toward Learning Robust and Invariant Representations with Alignment Regularization and Data Augmentation
Finally, we test this simple technique we identify (worst-case data augmentation with squared l2 norm alignment regularization) and show that the benefits of this method outrun those of the specially designed methods.
Ego4D: Around the World in 3,000 Hours of Egocentric Video
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite.
On the Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations
Data augmentation is one of the most popular techniques for improving the robustness of neural networks.
Squared $\ell_2$ Norm as Consistency Loss for Leveraging Augmented Data to Learn Robust and Invariant Representations
Data augmentation is one of the most popular techniques for improving the robustness of neural networks.
Smooth Kernels Improve Adversarial Robustness and Perceptually-Aligned Gradients
Recent research has shown that CNNs are often overly sensitive to high-frequency textural patterns.
High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks
We investigate the relationship between the frequency spectrum of image data and the generalization behavior of convolutional neural networks (CNN).
