It is shown in a variety of image classification settings and on several datasets, that quasibinary classifiers are considerably better in classification settings where regular binary and softmax classifiers suffer, including zero-label and multi-label classification.
It is demonstrated that matrix multiplication can be reformulated as a series of convolutions by exploiting a special structure in the matrix using the Fast Fourier Trans-form (FFT), reducing the time complexity to O ( q 2 log q ) .
This paper studies what happens to the rest of the model when a class is forgotten, using a label-conditioned energy-based model (EBM) that assigns per-class energies, making the effect directly observable.
Syed Ali Ahmed, Syed Bilal Ahsan, Muhammad Zaigham Zaheer National University of Computer et al.· 0 citations
DiD is introduced, a label-free conversion method that exclusively trains the linear-attention backbone by aligning detector-facing interface tensors with those of a frozen Softmax teacher, and substantially outperforms established baselines and matches supervised, fully trained linear models.
Huai-Yuan Qin, Gabriel James Goenawan, Zihang Lin et al.· 1 citation
Class-wise Covariance Regularization is proposed, which aligns the predicted covariance structure of class confidences with the semantic correlations encoded in pretrained text embed-dings with the geometric consistency of the class space throughout fine-tuning, resulting in more stable and interpretable confidence dis...
Ao Zhou, Zhi-Wei Jiang, Zi-Feng Cheng et al.· 0 citations
This thesis builds on an existing diagnostics toolkit mainly for t-SNE and UMAP and turns it into a more accessible package for interested practitioners, while also extending it with diagnostics tools.
Kasra Amirani, S. Huisman, E. V. van Nieuwenburg· 0 citations
Visual classifiers are expected to generalize under data shifts, target shifts, and their combinations, yet most existing methods focus on domain invariance while failing to address intra-image predictive sufficiency. We investigate the structural hypothesis that each image contains a sample-adaptive oracle intra-image...
Zhaorui Tan, Weimiao Yu, Xi Yang· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
