Due to their size, the capability of these networks has increased tremendously, but this has come at the cost of a significant increase in necessary compute.

We propose a method called clustered conformal prediction that clusters together classes having "similar" conformal

In Figure 1, we compare our LMC framework with the baseline Softmax, and present qualitative results on the TinyImageNet dataset. Below, we discuss them in more detail. AUROC is a widely-used threshold-independent evaluation metric. Both authors contributed equally to the work. Before entering the inference process, similar to our framework, Softmax also pre-stores certain CLIP and DINO features to make the inference process more efficient.

In recent years, transformer networks [V aswani et al., 2017] have been established as a fundamental neural architecture powering state-of-the-art results in many applications, including language

In recent years, transformer networks [V aswani et al., 2017] have been established as a fundamental neural architecture powering state-of-the-art results in many applications, including language

I{ } is the indicator function. It's sufficient to prove that the denominator converges to that of softmax at each point We have shown that softmax is translational invariant w.r.t. Without the loss of generality, we use τ = 1 in the following proof. To begin with, we prove the first equation and then give the proof of the second part of Theorem 3.3. We introduce some extra notations that are used throughout the proof.