MiTA Attention: Efficient Fast-Weight Scaling via a Mixture of Top-k Activations

The attention operator in Transformers can be viewed as a two-layer fast-weight MLP, whose weights are dynamically instantiated from input tokens and whose width equals sequence length N. As the context extends, the expressive capacity of such an N-width MLP increases, but scaling its fast weights becomes prohibitively expensive for extremely long sequences. Recently, this fast-weight scaling perspective has motivated the Mixture-of-Experts (MoE) attention, which partitions the sequence into fast-weight experts and sparsely routes the tokens to them. In this paper, we elevate this perspective to a unifying framework for a wide range of efficient attention methods by interpreting them as scaling fast weights through routing and/or compression. Then we propose a compress-and-route strategy, which compresses the N-width MLP into a narrower one using a small set of landmark queries and constructs deformable experts by gathering top-k activated key-value pairs for each landmark query. We call this strategy a Mixture of Top-k Activations (MiTA), and refer to the resulting efficient mechanism as MiTA attention. Preliminary experiments on vision tasks demonstrate the promise of our MiTA attention and motivate further investigation on its optimization and broader applications in more challenging settings.

Rethinking Decoders for Transformer-based Semantic Segmentation: Compression is All You Need

State-of-the-art methods for Transformer-based semantic segmentation typically adopt Transformer decoders that are used to extract additional embeddings from image embeddings via cross-attention, refine either or both types of embeddings via self-attention, and project image embeddings onto the additional embeddings via dot-product. Despite their remarkable success, these empirical designs still lack theoretical justifications or interpretations, thus hindering potentially principled improvements. In this paper, we argue that there are fundamental connections between semantic segmentation and compression, especially between the Transformer decoders and Principal Component Analysis (PCA). From such a perspective, we derive a white-box, fully attentional DEcoder for PrIncipled semantiC segemenTation (DEPICT), with the interpretations as follows: 1) the self-attention operator refines image embeddings to construct an ideal principal subspace that aligns with the supervision and retains most information; 2) the cross-attention operator seeks to find a low-rank approximation of the refined image embeddings, which is expected to be a set of orthonormal bases of the principal subspace and corresponds to the predefined classes; 3) the dot-product operation yields compact representation for image embeddings as segmentation masks. Experiments conducted on dataset ADE20K find that DEPICT consistently outperforms its black-box counterpart, Segmenter, and it is light weight and more robust.