SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
hub
The caltech-ucsd birds-200-2011 dataset
10 Pith papers cite this work. Polarity classification is still indexing.
hub tools
citation-role summary
citation-polarity summary
representative citing papers
FIKA-Bench is a leakage-aware benchmark of 311 instances showing that even the best large multimodal models and tool-equipped agents reach only 25.1% accuracy on fine-grained recognition questions that require external evidence search and verification.
RaPO reduces catastrophic forgetting in visual continual learning by shaping rewards around policy drift and stabilizing advantages with cross-task exponential moving averages during reinforcement fine-tuning of multimodal models.
CNN classifiers work by holographic superposition and destructive interference in pixel space rather than selecting cleaned features, as proven by a new adjoint inversion framework that also yields a covariance-volume channel selection algorithm.
AVA-Bench evaluates vision foundation models by disentangling 14 atomic visual abilities with aligned training-test distributions to reveal precise ability fingerprints.
Exploiting linear structure in VLM embeddings, a synthetic-data pre-training method yields background-invariant representations that exceed 90% worst-group accuracy on Waterbirds even under 100% spurious correlation with no minority examples in training.
S2FT replaces the sparse-spectrum assumption of prior Fourier PEFT with a learned rearrangement that maps a pre-estimated weight change into a domain where few spectral coefficients suffice.
λ-Orthogonality regularization enables distribution-specific adaptation of representations via affine transformations while retaining original learned structures.
ShellfishNet is a new benchmark of 8,691 images across 32 mollusc taxa for evaluating vision models on real-world underwater ecological monitoring tasks including robustness to degradation.
citing papers explorer
-
Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning
SPA unlocks patch-level features in CLIP for class-incremental learning via semantic-guided selection and optimal transport alignment with class descriptions, plus projectors and pseudo-feature replay to reduce forgetting.
-
FIKA-Bench: From Fine-grained Recognition to Fine-Grained Knowledge Acquisition
FIKA-Bench is a leakage-aware benchmark of 311 instances showing that even the best large multimodal models and tool-equipped agents reach only 25.1% accuracy on fine-grained recognition questions that require external evidence search and verification.
-
Overcoming Catastrophic Forgetting in Visual Continual Learning with Reinforcement Fine-Tuning
RaPO reduces catastrophic forgetting in visual continual learning by shaping rewards around policy drift and stabilizing advantages with cross-task exponential moving averages during reinforcement fine-tuning of multimodal models.
-
Adjoint Inversion Reveals Holographic Superposition and Destructive Interference in CNN Classifiers
CNN classifiers work by holographic superposition and destructive interference in pixel space rather than selecting cleaned features, as proven by a new adjoint inversion framework that also yields a covariance-volume channel selection algorithm.
-
AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models
AVA-Bench evaluates vision foundation models by disentangling 14 atomic visual abilities with aligned training-test distributions to reveal precise ability fingerprints.
-
Birds of a Feather Flock Together: Background-Invariant Representations via Linear Structure in VLMs
Exploiting linear structure in VLM embeddings, a synthetic-data pre-training method yields background-invariant representations that exceed 90% worst-group accuracy on Waterbirds even under 100% spurious correlation with no minority examples in training.
-
S2FT: Parameter-Efficient Fine-Tuning in Sparse Spectrum Domain
S2FT replaces the sparse-spectrum assumption of prior Fourier PEFT with a learned rearrangement that maps a pre-estimated weight change into a domain where few spectral coefficients suffice.
-
$\boldsymbol{\lambda}$-Orthogonality Regularization for Compatible Representation Learning
λ-Orthogonality regularization enables distribution-specific adaptation of representations via affine transformations while retaining original learned structures.
-
ShellfishNet: A Domain-Specific Benchmark for Visual Recognition of Marine Molluscs
ShellfishNet is a new benchmark of 8,691 images across 32 mollusc taxa for evaluating vision models on real-world underwater ecological monitoring tasks including robustness to degradation.
- Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering