Smaller self-supervised ViTs localize objects better via attention than larger ViTs, enabling A² to decouple localization from feature extraction for competitive performance on distribution-shifted benchmarks.
Wichmann, and Wieland Brendel
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
representative citing papers
CAML meta-learns a progressively refined inductive bias from active-learning queries to improve robustness to spurious correlations, reporting accuracy gains on minority groups across several benchmarks.
Spatial-frequency biases in neurally aligned DCNNs emerge from human-like representations but do not primarily drive their adversarial robustness advantages.
Alignment of vision-language models with human V1-V3 early visual cortex negatively predicts resistance to sycophantic gaslighting attacks.
Optimized 3x3 adversarial image filters based on edge detection generate transferable untargeted attacks on neural networks with 30-80% success using only one pass and far fewer parameters than prior methods.
ShapeY is a benchmark dataset and nearest-neighbor protocol that measures shape-based recognition in vision models, revealing that even state-of-the-art networks fail to generalize consistently across 3D viewpoints and non-shape appearance changes.
A plug-and-play Anonymizing Adapter Module removes private information from video latent features using self-supervised privacy objectives and consistency losses while retaining utility on action recognition, temporal detection, and anomaly tasks.
Zebrafish tectal subcircuits are dissociated into spike-efficient information gating and feedback-like robustness stabilization, then transferred to improve ResNet efficiency and noise tolerance.
Sparse-to-dense 3D segmentation from 2D slices shows divergent regularization needs: 2D benefits from strong augmentation and soft labels while 3D does not, and human-centric preprocessing harms performance.
Feedback Former improves cell image segmentation accuracy by feeding detailed feature maps back from near the output to lower transformer layers, outperforming non-feedback baselines with lower computational cost on three datasets.
Advocates integrating naturalistic paradigms and AI progress into cognitive science to develop generalizable models of natural behavior while retaining experimental control and theoretical insight.
Introduces IFM loss regularization for CNNs to learn correlated discriminative features, tested on shiftedMNIST dataset.
citing papers explorer
-
$A^2$: Smaller Self-Supervised ViTs Localize Better than Larger Ones
Smaller self-supervised ViTs localize objects better via attention than larger ViTs, enabling A² to decouple localization from feature extraction for competitive performance on distribution-shifted benchmarks.
-
Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations
CAML meta-learns a progressively refined inductive bias from active-learning queries to improve robustness to spurious correlations, reporting accuracy gains on minority groups across several benchmarks.
-
Dissociating spatial frequency reliance from adversarial robustness advantages in neurally guided deep convolutional neural networks
Spatial-frequency biases in neurally aligned DCNNs emerge from human-like representations but do not primarily drive their adversarial robustness advantages.
-
Gaslight, Gatekeep, V1-V3: Early Visual Cortex Alignment Shields Vision-Language Models from Sycophantic Manipulation
Alignment of vision-language models with human V1-V3 early visual cortex negatively predicts resistance to sycophantic gaslighting attacks.
-
Almost for Free: Crafting Adversarial Examples with Convolutional Image Filters
Optimized 3x3 adversarial image filters based on edge detection generate transferable untargeted attacks on neural networks with 30-80% success using only one pass and far fewer parameters than prior methods.
-
ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching
ShapeY is a benchmark dataset and nearest-neighbor protocol that measures shape-based recognition in vision models, revealing that even state-of-the-art networks fail to generalize consistently across 3D viewpoints and non-shape appearance changes.
-
Privacy Beyond Pixels: Latent Anonymization for Privacy-Preserving Video Understanding
A plug-and-play Anonymizing Adapter Module removes private information from video latent features using self-supervised privacy objectives and consistency losses while retaining utility on action recognition, temporal detection, and anomaly tasks.
-
Dual-axis attribution of zebrafish tectal microcircuits for energy-efficient and robust neurocomputing
Zebrafish tectal subcircuits are dissociated into spike-efficient information gating and feedback-like robustness stabilization, then transferred to improve ResNet efficiency and noise tolerance.
-
Optimization in Sparse 2D to Dense 3D Weakly Supervised Learning: Application to Multi-Label Segmentation of Large ex vivo MRI Data
Sparse-to-dense 3D segmentation from 2D slices shows divergent regularization needs: 2D benefits from strong augmentation and soft labels while 3D does not, and human-centric preprocessing harms performance.
-
Accuracy Improvement of Cell Image Segmentation Using Feedback Former
Feedback Former improves cell image segmentation accuracy by feeding detailed feature maps back from near the output to lower transformer layers, outperforming non-feedback baselines with lower computational cost on three datasets.
-
Naturalistic Computational Cognitive Science: Towards generalizable models and theories that capture the full range of natural behavior
Advocates integrating naturalistic paradigms and AI progress into cognitive science to develop generalizable models of natural behavior while retaining experimental control and theoretical insight.
-
Learning to Find Correlated Features by Maximizing Information Flow in Convolutional Neural Networks
Introduces IFM loss regularization for CNNs to learn correlated discriminative features, tested on shiftedMNIST dataset.