In generalized contrastive learning with imbalanced classes, optimal representations collapse to class means whose angular geometry is determined by class proportions via convex optimization, and extreme imbalance causes all minority classes to collapse to one vector.
Deep Residual Learning for Image Recognition , year=
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
representative citing papers
LHSD uses spectral filtering on the log-density Hessian to isolate tangent directions from noise and estimate local intrinsic dimension scalably via Stochastic Lanczos Quadrature.
A learnable nonlocal block that mimics classical neighbor matching and collaborative filtering on multiscale features produces competitive RAW denoising with far fewer parameters than current deep models and generalizes across sensors.
Q-Align trains LMMs on discrete text-defined levels for visual scoring, achieving SOTA on IQA, IAA, and VQA while unifying the tasks in OneAlign.
A graph-regulated disentangling Mamba model with sparse tokens achieves 93.94% accuracy classifying tree species from MODIS time series in Alberta and outperforms twelve prior models.
STAR-IOD applies scale-decoupled topology alignment and K-Means-based pseudo-label refinement to reduce catastrophic forgetting in remote sensing incremental object detection, reporting 1.7% and 2.1% mAP gains on new DIOR-IOD and DOTA-IOD datasets.
A novel loss function enables effective segmentation training from summary statistics combined with minimal weak pixel supervision, outperforming statistics alone on medical imaging tasks.
VLMs recover reliable population-level trends in climate change visual discourse on social media even when per-image accuracy is only moderate.
Invariant and equivariant semi-supervised learning improves multi-task detection and segmentation performance on partially labeled vision datasets compared to supervised baselines.
citing papers explorer
-
Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets
In generalized contrastive learning with imbalanced classes, optimal representations collapse to class means whose angular geometry is determined by class proportions via convex optimization, and extreme imbalance causes all minority classes to collapse to one vector.
-
Local Hessian Spectral Filtering for Robust Intrinsic Dimension Estimation
LHSD uses spectral filtering on the log-density Hessian to isolate tangent directions from noise and estimate local intrinsic dimension scalably via Stochastic Lanczos Quadrature.
-
Learned Nonlocal Feature Matching and Filtering for RAW Image Denoising
A learnable nonlocal block that mimics classical neighbor matching and collaborative filtering on multiscale features produces competitive RAW denoising with far fewer parameters than current deep models and generalizes across sensors.
-
Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels
Q-Align trains LMMs on discrete text-defined levels for visual scoring, achieving SOTA on IQA, IAA, and VQA while unifying the tasks in OneAlign.
-
A Novel Graph-Regulated Disentangling Mamba Model with Sparse Tokens for Enhanced Tree Species Classification from MODIS Time Series
A graph-regulated disentangling Mamba model with sparse tokens achieves 93.94% accuracy classifying tree species from MODIS time series in Alberta and outperforms twelve prior models.
-
STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detection
STAR-IOD applies scale-decoupled topology alignment and K-Means-based pseudo-label refinement to reduce catastrophic forgetting in remote sensing incremental object detection, reporting 1.7% and 2.1% mAP gains on new DIOR-IOD and DOTA-IOD datasets.
-
Learning to Segment using Summary Statistics and Weak Supervision
A novel loss function enables effective segmentation training from summary statistics combined with minimal weak pixel supervision, outperforming statistics alone on medical imaging tasks.
-
From Codebooks to VLMs: Evaluating Automated Visual Discourse Analysis for Climate Change on Social Media
VLMs recover reliable population-level trends in climate change visual discourse on social media even when per-image accuracy is only moderate.
-
Multi-task learning on partially labeled datasets via invariant/equivariant semi-supervised learning
Invariant and equivariant semi-supervised learning improves multi-task detection and segmentation performance on partially labeled vision datasets compared to supervised baselines.