ImageNet-S
PulseAugur coverage of ImageNet-S — every cluster mentioning ImageNet-S across labs, papers, and developer communities, ranked by signal.
-
LAS-CLIP adapts CLIP visual encoder without parameter changes
Researchers have introduced LAS-CLIP, a novel method for adapting CLIP's visual encoder without altering its original parameters. This approach utilizes a compact MaskAdapter to generate attention biases, which are then…
-
New training method enhances visual model generalization and robustness
Researchers have developed a new training method called Subset-Selected Counterfactual Augmentation (SS-CA) to improve the causal reasoning of visual models. This technique uses attribution methods to identify critical …
-
BareBones benchmark reveals Vision-Language Models suffer texture bias cliff
Researchers have introduced BareBones, a new benchmark designed to test the geometric comprehension abilities of Vision-Language Models (VLMs). The benchmark uses pixel-level silhouettes to evaluate if VLMs can understa…