Skip to main content
Search

# Class-Incremental Learning

4 related articles

Subscribe to updates
  1. arXiv

    TAP keeps CLIP frozen and still learns new classes, reaching 83.05% final-stage accuracy on ImageNet-R

    Class-incremental learning usually keeps changing pre-trained representations through prompt learning or adapters, at the cost of optimization overhead and disturbance to old-class feature structure. TAP freezes both CLIP encoders and accumulates each class's mean and within-class scatter in the frozen embedding space, while learning class-specific text-template weights from current-task images. Across nine datasets under two incremental protocols, TAP attains the highest average incremental and final-stage accuracies among the compared methods, with 83.05% final-stage accuracy on ImageNet-R under B0/Inc20.

  2. arXiv

    CLIP incremental learning stops relying only on [CLS] and [EOS]: PACE feeds patch and token detail into the decision and leads last accuracy on nine benchmarks

    CLIP-based class-incremental learning has mostly matched the global visual [CLS] and textual [EOS] representations across modalities, leaving patch-level visual detail and token-level textual semantics out of the final match. PACE selects the top-k visual patches and textual tokens most related to the global representations from the frozen CLIP encoders, injects that local information into the global representations through a cross-modal fusion module, and constrains updates of the shared fusion weights with subspace projection. Across nine benchmark datasets, PACE reports higher last and average accuracy than the listed comparison methods, for example a last accuracy of 93.94 on Cars B0 Inc10.

  3. arXiv

    Concepts that arrive late can still learn from discarded images: RetroCBM stores only statistics and lifts mean incremental accuracy 18.1% over the strongest exemplar-free baseline

    Exemplar-free class-incremental learning requires models to learn new classes in sequence without keeping old training images, and concept bottleneck models often fail to let newly named concepts contribute to old-class predictions once the concept vocabulary expands. RetroCBM stores a small set of statistics linking frozen visual features to vision-language model embeddings before images are discarded, then uses them to recover the same predictor that class-balanced ridge regression on all images seen so far would give, and reprojects those statistics into the expanded concept space to reweight old classes. Across 16 settings on six datasets it beats interpretable methods, with an 18.1% relative gain in mean average incremental accuracy over CI-CBM, the strongest exemplar-free baseline.

  4. arXiv

    PatchAdaNet does class-incremental learning without storing old samples: frozen patch features plus adapters reach 65.9% on CIFAR-10

    PatchAdaNet splits each image into patches, trains an independent patch autoencoder per position on external data and freezes them permanently, then uses learnable adapters to build whole-image representations, enabling unsupervised class-incremental classification without storing any past samples. A fixed-size Global Feature Centroid, a running average of adapter outputs, penalizes representation drift, and EWC constrains the adapters. On the 5-split CIFAR-10 protocol the CNN and ViT variants reach 65.9% and 64.5% respectively, both without a replay buffer.

You’re all caught up